Daily Papers

Rising concern for the societal implications of artificial intelligence systems has inspired a wave of academic and journalistic literature in which deployed systems are audited for harm by investigators from outside the organizations deploying the algorithms. However, it remains challenging for practitioners to identify the harmful repercussions of their own systems prior to deployment, and, once deployed, emergent issues can become difficult or impossible to trace back to their source. In this paper, we introduce a framework for algorithmic auditing that supports artificial intelligence system development end-to-end, to be applied throughout the internal organization development lifecycle. Each stage of the audit yields a set of documents that together form an overall audit report, drawing on an organization's values or principles to assess the fit of decisions made throughout the process. The proposed auditing framework is intended to contribute to closing the accountability gap in the development and deployment of large-scale artificial intelligence systems by embedding a robust process to ensure audit integrity.

Data collected from the real world tends to be biased, unbalanced, and at risk of exposing sensitive and private information. This reality has given rise to the idea of creating synthetic datasets to alleviate risk, bias, harm, and privacy concerns inherent in the real data. This concept relies on Generative AI models to produce unbiased, privacy-preserving synthetic data while being true to the real data. In this new paradigm, how can we tell if this approach delivers on its promises? We present an auditing framework that offers a holistic assessment of synthetic datasets and AI models trained on them, centered around bias and discrimination prevention, fidelity to the real data, utility, robustness, and privacy preservation. We showcase our framework by auditing multiple generative models on diverse use cases, including education, healthcare, banking, human resources, and across different modalities, from tabular, to time-series, to natural language. Our use cases demonstrate the importance of a holistic assessment in order to ensure compliance with socio-technical safeguards that regulators and policymakers are increasingly enforcing. For this purpose, we introduce the trust index that ranks multiple synthetic datasets based on their prescribed safeguards and their desired trade-offs. Moreover, we devise a trust-index-driven model selection and cross-validation procedure via auditing in the training loop that we showcase on a class of transformer models that we dub TrustFormers, across different modalities. This trust-driven model selection allows for controllable trust trade-offs in the resulting synthetic data. We instrument our auditing framework with workflows that connect different stakeholders from model development to audit and certification via a synthetic data auditing report.

The rapid rise of compound AI systems (a.k.a., AI agents) is reshaping the labor market, raising concerns about job displacement, diminished human agency, and overreliance on automation. Yet, we lack a systematic understanding of the evolving landscape. In this paper, we address this gap by introducing a novel auditing framework to assess which occupational tasks workers want AI agents to automate or augment, and how those desires align with the current technological capabilities. Our framework features an audio-enhanced mini-interview to capture nuanced worker desires and introduces the Human Agency Scale (HAS) as a shared language to quantify the preferred level of human involvement. Using this framework, we construct the WORKBank database, building on the U.S. Department of Labor's O*NET database, to capture preferences from 1,500 domain workers and capability assessments from AI experts across over 844 tasks spanning 104 occupations. Jointly considering the desire and technological capability divides tasks in WORKBank into four zones: Automation "Green Light" Zone, Automation "Red Light" Zone, R&D Opportunity Zone, Low Priority Zone. This highlights critical mismatches and opportunities for AI agent development. Moving beyond a simple automate-or-not dichotomy, our results reveal diverse HAS profiles across occupations, reflecting heterogeneous expectations for human involvement. Moreover, our study offers early signals of how AI agent integration may reshape the core human competencies, shifting from information-focused skills to interpersonal ones. These findings underscore the importance of aligning AI agent development with human desires and preparing workers for evolving workplace dynamics.

Automated ad targeting on social media is opaque, creating risks of exploitation and invisibility to external scrutiny. Users may be steered toward harmful content while independent auditing of these processes remains blocked. Large Language Models (LLMs) raise a new concern: the potential to reverse-engineer sensitive user attributes from exposure alone. We introduce a multi-stage auditing framework to investigate these risks. First, a large-scale audit of over 435,000 ad impressions delivered to 891 Australian Facebook users reveals algorithmic biases, including disproportionate Gambling and Politics ads shown to socioeconomically vulnerable and politically aligned groups. Second, a multimodal LLM can reconstruct users' demographic profiles from ad streams, outperforming census-based baselines and matching or exceeding human performance. Our results provide the first empirical evidence that ad streams constitute rich digital footprints for public AI inference, highlighting urgent privacy risks and the need for content-level auditing and governance.

As large language models (LLMs) are increasingly integrated into social decision-making, understanding their political positioning and alignment behavior is critical for safety and fairness. This study presents a sociotechnical audit of 26 prominent LLMs, triangulating their positions across three psychometric inventories (Political Compass, SapplyValues, 8 Values) and evaluating their performance on a large-scale news labeling task (N approx 27{,}000). Our results reveal a strong clustering of models in the Libertarian-Left region of the ideological space, encompassing 96.3% of the cohort. Alignment signals appear to be consistent architectural traits rather than stochastic noise (η^2 > 0.90); however, we identify substantial discrepancies in measurement validity. In particular, the Political Compass exhibits a strong negative correlation with cultural progressivism (r=-0.64) when compared against multi-axial instruments, suggesting a conflation of social conservatism with authoritarianism in this context. We further observe a significant divergence between open-weights and closed-source models, with the latter displaying markedly higher cultural progressivism scores (p<10^{-25}). In downstream media analysis, models exhibit a systematic "center-shift," frequently categorizing neutral articles as left-leaning, alongside an asymmetric detection capability in which "Far Left" content is identified with greater accuracy (19.2%) than "Far Right" content (2.0%). These findings suggest that single-axis evaluations are insufficient and that multidimensional auditing frameworks are necessary to characterize alignment behavior in deployed LLMs. Our code and data will be made public.

The Model Context Protocol (MCP) has emerged as a standardized interface enabling seamless integration between Large Language Models (LLMs) and external data sources and tools. While MCP significantly reduces development complexity and enhances agent capabilities, its openness and extensibility introduce critical security vulnerabilities that threaten system trustworthiness and user data protection. This paper systematically analyzes the security landscape of MCP-based systems, identifying three principal threat categories: (1) agent hijacking attacks stemming from protocol design deficiencies; (2) traditional web vulnerabilities in MCP servers; and (3) supply chain security. To address these challenges, we comprehensively survey existing defense strategies, examining both proactive server-side scanning approaches, ranging from layered detection pipelines and agentic auditing frameworks to zero-trust registry systems, and runtime interaction monitoring solutions that provide continuous oversight and policy enforcement. Our analysis reveals that MCP security fundamentally represents a paradigm shift where the attack surface extends from traditional code execution to semantic interpretation of natural language metadata, necessitating novel defense mechanisms tailored to this unique threat model.

Large language models (LLMs) mark a key shift in natural language processing (NLP), having advanced text generation, translation, and domain-specific reasoning. Closed-source models like GPT-4, powered by proprietary datasets and extensive computational resources, lead with state-of-the-art performance today. However, they face criticism for their "black box" nature and for limiting accessibility in a manner that hinders reproducibility and equitable AI development. By contrast, open-source initiatives like LLaMA and BLOOM prioritize democratization through community-driven development and computational efficiency. These models have significantly reduced performance gaps, particularly in linguistic diversity and domain-specific applications, while providing accessible tools for global researchers and developers. Notably, both paradigms rely on foundational architectural innovations, such as the Transformer framework by Vaswani et al. (2017). Closed-source models excel by scaling effectively, while open-source models adapt to real-world applications in underrepresented languages and domains. Techniques like Low-Rank Adaptation (LoRA) and instruction-tuning datasets enable open-source models to achieve competitive results despite limited resources. To be sure, the tension between closed-source and open-source approaches underscores a broader debate on transparency versus proprietary control in AI. Ethical considerations further highlight this divide. Closed-source systems restrict external scrutiny, while open-source models promote reproducibility and collaboration but lack standardized auditing documentation frameworks to mitigate biases. Hybrid approaches that leverage the strengths of both paradigms are likely to shape the future of LLM innovation, ensuring accessibility, competitive technical performance, and ethical deployment.

As Large Language Models (LLMs) become more pervasive across various users and scenarios, identifying potential issues when using these models becomes essential. Examples of such issues include: bias, inconsistencies, and hallucination. Although auditing the LLM for these problems is often warranted, such a process is neither easy nor accessible for most. An effective method is to probe the LLM using different versions of the same question. This could expose inconsistencies in its knowledge or operation, indicating potential for bias or hallucination. However, to operationalize this auditing method at scale, we need an approach to create those probes reliably and automatically. In this paper we propose the LLMAuditor framework which is an automatic, and scalable solution, where one uses a different LLM along with human-in-the-loop (HIL). This approach offers verifiability and transparency, while avoiding circular reliance on the same LLM, and increasing scientific rigor and generalizability. Specifically, LLMAuditor includes two phases of verification using humans: standardized evaluation criteria to verify responses, and a structured prompt template to generate desired probes. A case study using questions from the TruthfulQA dataset demonstrates that we can generate a reliable set of probes from one LLM that can be used to audit inconsistencies in a different LLM. This process is enhanced by our structured prompt template with HIL, which not only boosts the reliability of our approach in auditing but also yields the delivery of less hallucinated results. The novelty of our research stems from the development of a comprehensive, general-purpose framework that includes a HIL verified prompt template for auditing responses generated by LLMs.

As Large Language Model (LLM) agents are increasingly tasked with high-stakes autonomous decision-making, the transparency of their reasoning processes has become a critical safety concern. While Chain-of-Thought (CoT) prompting allows agents to generate human-readable reasoning traces, it remains unclear whether these traces are faithful generative drivers of the model's output or merely post-hoc rationalizations. We introduce Project Ariadne, a novel XAI framework that utilizes Structural Causal Models (SCMs) and counterfactual logic to audit the causal integrity of agentic reasoning. Unlike existing interpretability methods that rely on surface-level textual similarity, Project Ariadne performs hard interventions (do-calculus) on intermediate reasoning nodes -- systematically inverting logic, negating premises, and reversing factual claims -- to measure the Causal Sensitivity (φ) of the terminal answer. Our empirical evaluation of state-of-the-art models reveals a persistent Faithfulness Gap. We define and detect a widespread failure mode termed Causal Decoupling, where agents exhibit a violation density (ρ) of up to 0.77 in factual and scientific domains. In these instances, agents arrive at identical conclusions despite contradictory internal logic, proving that their reasoning traces function as "Reasoning Theater" while decision-making is governed by latent parametric priors. Our findings suggest that current agentic architectures are inherently prone to unfaithful explanation, and we propose the Ariadne Score as a new benchmark for aligning stated logic with model action.

Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety problem when individual agents form a coalition and collude to pursue secondary goals and degrade the joint objective. In this paper, we present Colosseum, a framework for auditing LLM agents' collusive behavior in multi-agent settings. We ground how agents cooperate through a Distributed Constraint Optimization Problem (DCOP) and measure collusion via regret relative to the cooperative optimum. Colosseum tests each LLM for collusion under different objectives, persuasion tactics, and network topologies. Through our audit, we show that most out-of-the-box models exhibited a propensity to collude when a secret communication channel was artificially formed. Furthermore, we discover ``collusion on paper'' when agents plan to collude in text but would often pick non-collusive actions, thus providing little effect on the joint task. Colosseum provides a new way to study collusion by measuring communications and actions in rich yet verifiable environments.

Large Language Models (LLM) have made significant advances in the recent past becoming more mainstream in Artificial Intelligence (AI) enabled human-facing applications. However, LLMs often generate stereotypical output inherited from historical data, amplifying societal biases and raising ethical concerns. This work introduces i) the Multi-Grain Stereotype Dataset, which includes 52,751 instances of gender, race, profession and religion stereotypic text and ii) a novel stereotype classifier for English text. We design several experiments to rigorously test the proposed model trained on the novel dataset. Our experiments show that training the model in a multi-class setting can outperform the one-vs-all binary counterpart. Consistent feature importance signals from different eXplainable AI tools demonstrate that the new model exploits relevant text features. We utilise the newly created model to assess the stereotypic behaviour of the popular GPT family of models and observe the reduction of bias over time. In summary, our work establishes a robust and practical framework for auditing and evaluating the stereotypic bias in LLM.

Membership inference attacks (MIAs) pose a critical privacy threat to fine-tuned large language models (LLMs), especially when models are adapted to domain-specific tasks using sensitive data. While prior black-box MIA techniques rely on confidence scores or token likelihoods, these signals are often entangled with a sample's intrinsic properties - such as content difficulty or rarity - leading to poor generalization and low signal-to-noise ratios. In this paper, we propose ICP-MIA, a novel MIA framework grounded in the theory of training dynamics, particularly the phenomenon of diminishing returns during optimization. We introduce the Optimization Gap as a fundamental signal of membership: at convergence, member samples exhibit minimal remaining loss-reduction potential, while non-members retain significant potential for further optimization. To estimate this gap in a black-box setting, we propose In-Context Probing (ICP), a training-free method that simulates fine-tuning-like behavior via strategically constructed input contexts. We propose two probing strategies: reference-data-based (using semantically similar public samples) and self-perturbation (via masking or generation). Experiments on three tasks and multiple LLMs show that ICP-MIA significantly outperforms prior black-box MIAs, particularly at low false positive rates. We further analyze how reference data alignment, model type, PEFT configurations, and training schedules affect attack effectiveness. Our findings establish ICP-MIA as a practical and theoretically grounded framework for auditing privacy risks in deployed LLMs.

Recent advances in multi-modal Large Language Models (M-LLMs) have demonstrated a powerful ability to synthesize implicit information from disparate sources, including images and text. These resourceful data from social media also introduce a significant and underexplored privacy risk: the inference of sensitive personal attributes from seemingly daily media content. However, the lack of benchmarks and comprehensive evaluations of state-of-the-art M-LLM capabilities hinders the research of private attribute profiling on social media. Accordingly, we propose (1) PRISM, the first multi-modal, multi-dimensional and fine-grained synthesized dataset incorporating a comprehensive privacy landscape and dynamic user history; (2) an Efficient evaluation framework that measures the cross-modal privacy inference capabilities of advanced M-LLM. Specifically, PRISM is a large-scale synthetic benchmark designed to evaluate cross-modal privacy risks. Its key feature is 12 sensitive attribute labels across a diverse set of multi-modal profiles, which enables targeted privacy analysis. These profiles are generated via a sophisticated LLM agentic workflow, governed by a prior distribution to ensure they realistically mimic social media users. Additionally, we propose a Multi-Agent Inference Framework that leverages a pipeline of specialized LLMs to enhance evaluation capabilities. We evaluate the inference capabilities of six leading M-LLMs (Qwen, Gemini, GPT-4o, GLM, Doubao, and Grok) on PRISM. The comparison with human performance reveals that these MLLMs significantly outperform in accuracy and efficiency, highlighting the threat of potential privacy risks and the urgent need for robust defenses.

As large language models (LLMs) like GPT-4 and Llama 3 become integral to educational contexts, concerns are mounting over the cultural biases, power imbalances, and ethical limitations embedded within these technologies. Though generative AI tools aim to enhance learning experiences, they often reflect values rooted in Western, Educated, Industrialized, Rich, and Democratic (WEIRD) cultural paradigms, potentially sidelining diverse global perspectives. This paper proposes a framework to assess and mitigate cultural bias within LLMs through the lens of applied multiplexity. Multiplexity, inspired by Senturk et al. and rooted in Islamic and other wisdom traditions, emphasizes the coexistence of diverse cultural viewpoints, supporting a multi-layered epistemology that integrates both empirical sciences and normative values. Our analysis reveals that LLMs frequently exhibit cultural polarization, with biases appearing in both overt responses and subtle contextual cues. To address inherent biases and incorporate multiplexity in LLMs, we propose two strategies: Contextually-Implemented Multiplex LLMs, which embed multiplex principles directly into the system prompt, influencing LLM outputs at a foundational level and independent of individual prompts, and Multi-Agent System (MAS)-Implemented Multiplex LLMs, where multiple LLM agents, each representing distinct cultural viewpoints, collaboratively generate a balanced, synthesized response. Our findings demonstrate that as mitigation strategies evolve from contextual prompting to MAS-implementation, cultural inclusivity markedly improves, evidenced by a significant rise in the Perspectives Distribution Score (PDS) and a PDS Entropy increase from 3.25\% at baseline to 98\% with the MAS-Implemented Multiplex LLMs. Sentiment analysis further shows a shift towards positive sentiment across cultures,...

Commercial LLM services often conceal internal reasoning traces while still charging users for every generated token, including those from hidden intermediate steps, raising concerns of token inflation and potential overbilling. This gap underscores the urgent need for reliable token auditing, yet achieving it is far from straightforward: cryptographic verification (e.g., hash-based signature) offers little assurance when providers control the entire execution pipeline, while user-side prediction struggles with the inherent variance of reasoning LLMs, where token usage fluctuates across domains and prompt styles. To bridge this gap, we present PALACE (Predictive Auditing of LLM APIs via Reasoning Token Count Estimation), a user-side framework that estimates hidden reasoning token counts from prompt-answer pairs without access to internal traces. PALACE introduces a GRPO-augmented adaptation module with a lightweight domain router, enabling dynamic calibration across diverse reasoning tasks and mitigating variance in token usage patterns. Experiments on math, coding, medical, and general reasoning benchmarks show that PALACE achieves low relative error and strong prediction accuracy, supporting both fine-grained cost auditing and inflation detection. Taken together, PALACE represents an important first step toward standardized predictive auditing, offering a practical path to greater transparency, accountability, and user trust.

Conventional evaluation methods for multimodal LLMs (MLLMs) lack interpretability and are often insufficient to fully disclose significant capability gaps across models. To address this, we introduce AuditDM, an automated framework that actively discovers and rectifies MLLM failure modes by auditing their divergence. AuditDM fine-tunes an MLLM as an auditor via reinforcement learning to generate challenging questions and counterfactual images that maximize disagreement among target models. Once trained, the auditor uncovers diverse, interpretable exemplars that reveal model weaknesses and serve as annotation-free data for rectification. When applied to SoTA models like Gemma-3 and PaliGemma-2, AuditDM discovers more than 20 distinct failure types. Fine-tuning on these discoveries consistently improves all models across 16 benchmarks, and enables a 3B model to surpass its 28B counterpart. Our results suggest that as data scaling hits diminishing returns, targeted model auditing offers an effective path to model diagnosis and improvement.

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel sociotechnically grounded audit framework that turns prior community-identified failure cases into eight measurable dimensions spanning answer text, sources, and citations. DeepTRACE uses statement-level analysis (decomposition, confidence scoring) and builds citation and factual-support matrices to audit how systems reason with and attribute evidence end-to-end. Using automated extraction pipelines for popular public models (e.g., GPT-4.5/5, You.com, Perplexity, Copilot/Bing, Gemini) and an LLM-judge with validated agreement to human raters, we evaluate both web-search engines and deep-research configurations. Our findings show that generative search engines and deep research agents frequently produce one-sided, highly confident responses on debate queries and include large fractions of statements unsupported by their own listed sources. Deep-research configurations reduce overconfidence and can attain high citation thoroughness, but they remain highly one-sided on debate queries and still exhibit large fractions of unsupported statements, with citation accuracy ranging from 40--80% across systems.

Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization by transforming existing, supervised datasets into a diversity of novel pretraining tasks, highlighting the benefits of meta-dataset curation. While successful in general-domain text, translating these data-centric approaches to biomedical language modeling remains challenging, as labeled biomedical datasets are significantly underrepresented in popular data hubs. To address this challenge, we introduce BigBIO a community library of 126+ biomedical NLP datasets, currently covering 12 task categories and 10+ languages. BigBIO facilitates reproducible meta-dataset curation via programmatic access to datasets and their metadata, and is compatible with current platforms for prompt engineering and end-to-end few/zero shot language model evaluation. We discuss our process for task schema harmonization, data auditing, contribution guidelines, and outline two illustrative use cases: zero-shot evaluation of biomedical prompts and large-scale, multi-task learning. BigBIO is an ongoing community effort and is available at https://github.com/bigscience-workshop/biomedical

The recently released ChatGPT model demonstrates unprecedented capabilities in zero-shot question-answering. In this work, we probe ChatGPT for its conversational understanding and introduce a conversational framework (protocol) that can be adopted in future studies. The Pok\'emon universe serves as an ideal testing ground for auditing ChatGPT's reasoning capabilities due to its closed world assumption. After bringing ChatGPT's background knowledge (on the Pok\'emon universe) to light, we test its reasoning process when using these concepts in battle scenarios. We then evaluate its ability to acquire new knowledge and include it in its reasoning process. Our ultimate goal is to assess ChatGPT's ability to generalize, combine features, and to acquire and reason over newly introduced knowledge from human feedback. We find that ChatGPT has prior knowledge of the Pokemon universe, which can reason upon in battle scenarios to a great extent, even when new information is introduced. The model performs better with collaborative feedback and if there is an initial phase of information retrieval, but also hallucinates occasionally and is susceptible to adversarial attacks.

Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs), yet most frameworks still aggregate agent outputs with majority voting. This heuristic discards the evidential structure of reasoning traces and is brittle under the confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which replaces voting with a path search over a Reasoning Tree that explicitly represents agreements and divergences among agent traces. AgentAuditor resolves conflicts by comparing reasoning branches at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator on majority-failure cases and rewards evidence-based minority selections over popular errors. AgentAuditor is agnostic to MAS setting, and we find across 5 popular settings that it yields up to 5% absolute accuracy improvement over a majority vote, and up to 3% over using LLM-as-Judge.

Smart contracts are decentralized applications built atop blockchains like Ethereum. Recent research has shown that large language models (LLMs) have potential in auditing smart contracts, but the state-of-the-art indicates that even GPT-4 can achieve only 30% precision (when both decision and justification are correct). This is likely because off-the-shelf LLMs were primarily pre-trained on a general text/code corpus and not fine-tuned on the specific domain of Solidity smart contract auditing. In this paper, we propose TrustLLM, a general framework that combines fine-tuning and LLM-based agents for intuitive smart contract auditing with justifications. Specifically, TrustLLM is inspired by the observation that expert human auditors first perceive what could be wrong and then perform a detailed analysis of the code to identify the cause. As such, TrustLLM employs a two-stage fine-tuning approach: it first tunes a Detector model to make decisions and then tunes a Reasoner model to generate causes of vulnerabilities. However, fine-tuning alone faces challenges in accurately identifying the optimal cause of a vulnerability. Therefore, we introduce two LLM-based agents, the Ranker and Critic, to iteratively select and debate the most suitable cause of vulnerability based on the output of the fine-tuned Reasoner model. To evaluate TrustLLM, we collected a balanced dataset with 1,734 positive and 1,810 negative samples to fine-tune TrustLLM. We then compared it with traditional fine-tuned models (CodeBERT, GraphCodeBERT, CodeT5, and UnixCoder) as well as prompt learning-based LLMs (GPT4, GPT-3.5, and CodeLlama-13b/34b). On a dataset of 263 real smart contract vulnerabilities, TrustLLM achieves an F1 score of 91.21% and an accuracy of 91.11%. The causes generated by TrustLLM achieved a consistency of about 38% compared to the ground truth causes.

While the existing literature on Differential Privacy (DP) auditing predominantly focuses on the centralized model (e.g., in auditing the DP-SGD algorithm), we advocate for extending this approach to audit Local DP (LDP). To achieve this, we introduce the LDP-Auditor framework for empirically estimating the privacy loss of locally differentially private mechanisms. This approach leverages recent advances in designing privacy attacks against LDP frequency estimation protocols. More precisely, through the analysis of numerous state-of-the-art LDP protocols, we extensively explore the factors influencing the privacy audit, such as the impact of different encoding and perturbation functions. Additionally, we investigate the influence of the domain size and the theoretical privacy loss parameters ε and δ on local privacy estimation. In-depth case studies are also conducted to explore specific aspects of LDP auditing, including distinguishability attacks on LDP protocols for longitudinal studies and multidimensional data. Finally, we present a notable achievement of our LDP-Auditor framework, which is the discovery of a bug in a state-of-the-art LDP Python package. Overall, our LDP-Auditor framework as well as our study offer valuable insights into the sources of randomness and information loss in LDP protocols. These contributions collectively provide a realistic understanding of the local privacy loss, which can help practitioners in selecting the LDP mechanism and privacy parameters that best align with their specific requirements. We open-sourced LDP-Auditor in https://github.com/hharcolezi/ldp-audit.

As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used during training, despite growing concerns about their reliability under realistic conditions. We ask whether MIAs can serve as admissible evidence in adversarial copyright disputes where an accused model developer may obfuscate training data while preserving semantic content, and formalize this setting through a judge-prosecutor-accused communication protocol. To test robustness under this protocol, we introduce SAGE (Structure-Aware SAE-Guided Extraction), a paraphrasing framework guided by Sparse Autoencoders (SAEs) that rewrites training data to alter lexical structure while preserving semantic content and downstream utility. Our experiments show that state-of-the-art MIAs degrade when models are fine-tuned on SAGE-generated paraphrases, indicating that their signals are not robust to semantics-preserving transformations. While some leakage remains in certain fine-tuning regimes, these results suggest that MIAs are brittle in adversarial settings and insufficient, on their own, as a standalone mechanism for copyright auditing of LLMs.

Under a unified operational definition, we define LLM memory as a persistent state written during pretraining, finetuning, or inference that can later be addressed and that stably influences outputs. We propose a four-part taxonomy (parametric, contextual, external, procedural/episodic) and a memory quadruple (location, persistence, write/access path, controllability). We link mechanism, evaluation, and governance via the chain write -> read -> inhibit/update. To avoid distorted comparisons across heterogeneous setups, we adopt a three-setting protocol (parametric only, offline retrieval, online retrieval) that decouples capability from information availability on the same data and timeline. On this basis we build a layered evaluation: parametric (closed-book recall, edit differential, memorization/privacy), contextual (position curves and the mid-sequence drop), external (answer correctness vs snippet attribution/faithfulness), and procedural/episodic (cross-session consistency and timeline replay, E MARS+). The framework integrates temporal governance and leakage auditing (freshness hits, outdated answers, refusal slices) and uncertainty reporting via inter-rater agreement plus paired tests with multiple-comparison correction. For updating and forgetting, we present DMM Gov: coordinating DAPT/TAPT, PEFT, model editing (ROME, MEND, MEMIT, SERAC), and RAG to form an auditable loop covering admission thresholds, rollout, monitoring, rollback, and change audits, with specs for timeliness, conflict handling, and long-horizon consistency. Finally, we give four testable propositions: minimum identifiability; a minimal evaluation card; causally constrained editing with verifiable forgetting; and when retrieval with small-window replay outperforms ultra-long-context reading. This yields a reproducible, comparable, and governable coordinate system for research and deployment.

Refusals - instances where large language models (LLMs) decline or fail to fully execute user instructions - are crucial for both AI safety and AI capabilities and the reduction of hallucinations in particular. These behaviors are learned during post-training, especially in instruction fine-tuning (IFT) and reinforcement learning from human feedback (RLHF). However, existing taxonomies and evaluation datasets for refusals are inadequate, often focusing solely on should-not-related (instead of cannot-related) categories, and lacking tools for auditing refusal content in black-box LLM outputs. We present a comprehensive framework for classifying LLM refusals: (a) a taxonomy of 16 refusal categories, (b) a human-annotated dataset of over 8,600 instances from publicly available IFT and RLHF datasets, (c) a synthetic dataset with 8,000 examples for each refusal category, and (d) classifiers trained for refusal classification. Our work enables precise auditing of refusal behaviors in black-box LLMs and automatic analyses of refusal patterns in large IFT and RLHF datasets. This facilitates the strategic adjustment of LLM refusals, contributing to the development of more safe and reliable LLMs.

The rapid scaling of AI has spurred a growing emphasis on ethical considerations in both development and practice. This has led to the formulation of increasingly sophisticated model auditing and reporting requirements, as well as governance frameworks to mitigate potential risks to individuals and society. At this critical juncture, we review the practical challenges of promoting responsible AI and transparency in informal sectors like OSS that support vital infrastructure and see widespread use. We focus on how model performance evaluation may inform or inhibit probing of model limitations, biases, and other risks. Our controlled analysis of 7903 Hugging Face projects found that risk documentation is strongly associated with evaluation practices. Yet, submissions (N=789) from the platform's most popular competitive leaderboard showed less accountability among high performers. Our findings can inform AI providers and legal scholars in designing interventions and policies that preserve open-source innovation while incentivizing ethical uptake.

The rapid integration of agentic AI into high-stakes real-world applications requires robust oversight mechanisms. The emerging field of AI Control (AIC) aims to provide such an oversight mechanism, but practical adoption depends heavily on implementation overhead. To study this problem better, we introduce the notion of Control tax -- the operational and financial cost of integrating control measures into AI pipelines. Our work makes three key contributions to the field of AIC: (1) we introduce a theoretical framework that quantifies the Control Tax and maps classifier performance to safety assurances; (2) we conduct comprehensive evaluations of state-of-the-art language models in adversarial settings, where attacker models insert subtle backdoors into code while monitoring models attempt to detect these vulnerabilities; and (3) we provide empirical financial cost estimates for control protocols and develop optimized monitoring strategies that balance safety and cost-effectiveness while accounting for practical constraints like auditing budgets. Our framework enables practitioners to make informed decisions by systematically connecting safety guarantees with their costs, advancing AIC through principled economic feasibility assessment across different deployment contexts.

The continuous growth of the e-commerce industry attracts fraudsters who exploit stolen credit card details. Companies often investigate suspicious transactions in order to retain customer trust and address gaps in their fraud detection systems. However, analysts are overwhelmed with an enormous number of alerts from credit card transaction monitoring systems. Each alert investigation requires from the fraud analysts careful attention, specialized knowledge, and precise documentation of the outcomes, leading to alert fatigue. To address this, we propose a fraud analyst assistant (FAA) framework, which employs multi-modal large language models (LLMs) to automate credit card fraud investigations and generate explanatory reports. The FAA framework leverages the reasoning, code execution, and vision capabilities of LLMs to conduct planning, evidence collection, and analysis in each investigation step. A comprehensive empirical evaluation of 500 credit card fraud investigations demonstrates that the FAA framework produces reliable and efficient investigations comprising seven steps on average. Thus we found that the FAA framework can automate large parts of the workload and help reduce the challenges faced by fraud analysts.

The complexity of the Generally Accepted Accounting Principles (GAAP) and the hierarchical structure of eXtensible Business Reporting Language (XBRL) filings make financial auditing increasingly difficult to automate and verify. While large language models (LLMs) have demonstrated strong capabilities in unstructured text understanding, their ability to reason over structured, interdependent, and taxonomy-driven financial documents remains largely unexplored. To fill this gap, we introduce FinAuditing, the first taxonomy-aligned, structure-aware, multi-document benchmark for evaluating LLMs on financial auditing tasks. Built from real US-GAAP-compliant XBRL filings, FinAuditing defines three complementary subtasks, FinSM for semantic consistency, FinRE for relational consistency, and FinMR for numerical consistency, each targeting a distinct aspect of structured auditing reasoning. We further propose a unified evaluation framework integrating retrieval, classification, and reasoning metrics across these subtasks. Extensive zero-shot experiments on 13 state-of-the-art LLMs reveal that current models perform inconsistently across semantic, relational, and mathematical dimensions, with accuracy drops of up to 60-90% when reasoning over hierarchical multi-document structures. Our findings expose the systematic limitations of modern LLMs in taxonomy-grounded financial reasoning and establish FinAuditing as a foundation for developing trustworthy, structure-aware, and regulation-aligned financial intelligence systems. The benchmark dataset is available at Hugging Face.

As Large Language Models (LLMs) gain wider adoption in various contexts, it becomes crucial to ensure they are reasonably safe, consistent, and reliable for an application at hand. This may require probing or auditing them. Probing LLMs with varied iterations of a single question could reveal potential inconsistencies in their knowledge or functionality. However, a tool for performing such audits with simple workflow and low technical threshold is lacking. In this demo, we introduce "AuditLLM," a novel tool designed to evaluate the performance of various LLMs in a methodical way. AuditLLM's core functionality lies in its ability to test a given LLM by auditing it using multiple probes generated from a single question, thereby identifying any inconsistencies in the model's understanding or operation. A reasonably robust, reliable, and consistent LLM should output semantically similar responses for a question asked differently or by different people. Based on this assumption, AuditLLM produces easily interpretable results regarding the LLM's consistencies from a single question that the user enters. A certain level of inconsistency has been shown to be an indicator of potential bias, hallucinations, and other issues. One could then use the output of AuditLLM to further investigate issues with the aforementioned LLM. To facilitate demonstration and practical uses, AuditLLM offers two key modes: (1) Live mode which allows instant auditing of LLMs by analyzing responses to real-time queries; (2) Batch mode which facilitates comprehensive LLM auditing by processing multiple queries at once for in-depth analysis. This tool is beneficial for both researchers and general users, as it enhances our understanding of LLMs' capabilities in generating responses, using a standardized auditing platform.

One of the most concrete measures to take towards meaningful AI accountability is to consequentially assess and report the systems' performance and impact. However, the practical nature of the "AI audit" ecosystem is muddled and imprecise, making it difficult to work through various concepts and map out the stakeholders involved in the practice. First, we taxonomize current AI audit practices as completed by regulators, law firms, civil society, journalism, academia, consulting agencies. Next, we assess the impact of audits done by stakeholders within each domain. We find that only a subset of AI audit studies translate to desired accountability outcomes. We thus assess and isolate practices necessary for effective AI audit results, articulating the observed connections between AI audit design, methodology and institutional context on its effectiveness as a meaningful mechanism for accountability.

Recent years have witnessed an interesting phenomenon in which users come together to interrogate potentially harmful algorithmic behaviors they encounter in their everyday lives. Researchers have started to develop theoretical and empirical understandings of these user driven audits, with a hope to harness the power of users in detecting harmful machine behaviors. However, little is known about user participation and their division of labor in these audits, which are essential to support these collective efforts in the future. Through collecting and analyzing 17,984 tweets from four recent cases of user driven audits, we shed light on patterns of user participation and engagement, especially with the top contributors in each case. We also identified the various roles user generated content played in these audits, including hypothesizing, data collection, amplification, contextualization, and escalation. We discuss implications for designing tools to support user driven audits and users who labor to raise awareness of algorithm bias.

Recent legislation required AI platforms to provide APIs for regulators to assess their compliance with the law. Research has nevertheless shown that platforms can manipulate their API answers through fairwashing. Facing this threat for reliable auditing, this paper studies the benefits of the joint use of platform scraping and of APIs. In this setup, we elaborate on the use of scraping to detect manipulated answers: since fairwashing only manipulates API answers, exploiting scraps may reveal a manipulation. To abstract the wide range of specific API-scrap situations, we introduce a notion of proxy that captures the consistency an auditor might expect between both data sources. If the regulator has a good proxy of the consistency, then she can easily detect manipulation and even bypass the API to conduct her audit. On the other hand, without a good proxy, relying on the API is necessary, and the auditor cannot defend against fairwashing. We then simulate practical scenarios in which the auditor may mostly rely on the API to conveniently conduct the audit task, while maintaining her chances to detect a potential manipulation. To highlight the tension between the audit task and the API fairwashing detection task, we identify Pareto-optimal strategies in a practical audit scenario. We believe this research sets the stage for reliable audits in practical and manipulation-prone setups.

AI audits are an increasingly popular mechanism for algorithmic accountability; however, they remain poorly defined. Without a clear understanding of audit practices, let alone widely used standards or regulatory guidance, claims that an AI product or system has been audited, whether by first-, second-, or third-party auditors, are difficult to verify and may exacerbate, rather than mitigate, bias and harm. To address this knowledge gap, we provide the first comprehensive field scan of the AI audit ecosystem. We share a catalog of individuals (N=438) and organizations (N=189) who engage in algorithmic audits or whose work is directly relevant to algorithmic audits; conduct an anonymous survey of the group (N=152); and interview industry leaders (N=10). We identify emerging best practices as well as methods and tools that are becoming commonplace, and enumerate common barriers to leveraging algorithmic audits as effective accountability mechanisms. We outline policy recommendations to improve the quality and impact of these audits, and highlight proposals with wide support from algorithmic auditors as well as areas of debate. Our recommendations have implications for lawmakers, regulators, internal company policymakers, and standards-setting bodies, as well as for auditors. They are: 1) require the owners and operators of AI systems to engage in independent algorithmic audits against clearly defined standards; 2) notify individuals when they are subject to algorithmic decision-making systems; 3) mandate disclosure of key components of audit findings for peer review; 4) consider real-world harm in the audit process, including through standardized harm incident reporting and response mechanisms; 5) directly involve the stakeholders most likely to be harmed by AI systems in the algorithmic audit process; and 6) formalize evaluation and, potentially, accreditation of algorithmic auditors.

The emergent phenomena of large foundation models have revolutionized natural language processing. However, evaluating these models presents significant challenges due to their size, capabilities, and deployment across diverse applications. Existing literature often focuses on individual aspects, such as benchmark performance or specific tasks, but fails to provide a cohesive process that integrates the nuances of diverse use cases with broader ethical and operational considerations. This work focuses on three key aspects: (1) Formalizing the Evaluation Process by providing a structured framework tailored to specific use-case contexts, (2) Offering Actionable Tools and Frameworks such as checklists and templates to ensure thorough, reproducible, and practical evaluations, and (3) Surveying Recent Work with a targeted review of advancements in LLM evaluation, emphasizing real-world applications.

Regulatory compliance auditing across diverse industrial domains requires heightened quality assurance and traceability. Present manual and intermittent approaches to such auditing yield significant challenges, potentially leading to oversights in the monitoring process. To address these issues, we introduce a real-time, multi-modal sensing system employing 3D time-of-flight and RGB cameras, coupled with unsupervised learning techniques on edge AI devices. This enables continuous object tracking thereby enhancing efficiency in record-keeping and minimizing manual interventions. While we validate the system in a knife sanitization context within agrifood facilities, emphasizing its prowess against occlusion and low-light issues with RGB cameras, its potential spans various industrial monitoring settings.

Leveraging large language models in real-world settings often entails a need to utilize domain-specific data and tools in order to follow the complex regulations that need to be followed for acceptable use. Within financial sectors, modern enterprises increasingly rely on Retrieval-Augmented Generation (RAG) systems to address complex compliance requirements in financial document workflows. However, existing solutions struggle to account for the inherent heterogeneity of data (e.g., text, tables, diagrams) and evolving nature of regulatory standards used in financial filings, leading to compromised accuracy in critical information extraction. We propose the FinSage framework as a solution, utilizing a multi-aspect RAG framework tailored for regulatory compliance analysis in multi-modal financial documents. FinSage introduces three innovative components: (1) a multi-modal pre-processing pipeline that unifies diverse data formats and generates chunk-level metadata summaries, (2) a multi-path sparse-dense retrieval system augmented with query expansion (HyDE) and metadata-aware semantic search, and (3) a domain-specialized re-ranking module fine-tuned via Direct Preference Optimization (DPO) to prioritize compliance-critical content. Extensive experiments demonstrate that FinSage achieves an impressive recall of 92.51% on 75 expert-curated questions derived from surpasses the best baseline method on the FinanceBench question answering datasets by 24.06% in accuracy. Moreover, FinSage has been successfully deployed as financial question-answering agent in online meetings, where it has already served more than 1,200 people.

Data catalogs play a crucial role in modern data-driven organizations by facilitating the discovery, understanding, and utilization of diverse data assets. However, ensuring their quality and reliability is complex, especially in open and large-scale data environments. This paper proposes a framework to automatically determine the quality of open data catalogs, addressing the need for efficient and reliable quality assessment mechanisms. Our framework can analyze various core quality dimensions, such as accuracy, completeness, consistency, scalability, and timeliness, offer several alternatives for the assessment of compatibility and similarity across such catalogs as well as the implementation of a set of non-core quality dimensions such as provenance, readability, and licensing. The goal is to empower data-driven organizations to make informed decisions based on trustworthy and well-curated data assets. The source code that illustrates our approach can be downloaded from https://www.github.com/jorge-martinez-gil/dataq/.

Auditing large language models for unexpected behaviors is critical to preempt catastrophic deployments, yet remains challenging. In this work, we cast auditing as an optimization problem, where we automatically search for input-output pairs that match a desired target behavior. For example, we might aim to find a non-toxic input that starts with "Barack Obama" that a model maps to a toxic output. This optimization problem is difficult to solve as the set of feasible points is sparse, the space is discrete, and the language models we audit are non-linear and high-dimensional. To combat these challenges, we introduce a discrete optimization algorithm, ARCA, that jointly and efficiently optimizes over inputs and outputs. Our approach automatically uncovers derogatory completions about celebrities (e.g. "Barack Obama is a legalized unborn" -> "child murderer"), produces French inputs that complete to English outputs, and finds inputs that generate a specific name. Our work offers a promising new tool to uncover models' failure-modes before deployment.

Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities. By transforming data from a scarce resource into a controllable asset, LLMs mitigate the bottlenecks imposed by the acquisition costs of real-world data for model training, evaluation, and system iteration. However, ensuring the high quality of LLM-generated synthetic data remains a critical challenge. Existing research primarily focuses on generation methodologies, with limited direct attention to the quality of the resulting data. Furthermore, most studies are restricted to single modalities, lacking a unified perspective across different data types. To bridge this gap, we propose the LLM Data Auditor framework. In this framework, we first describe how LLMs are utilized to generate data across six distinct modalities. More importantly, we systematically categorize intrinsic metrics for evaluating synthetic data from two dimensions: quality and trustworthiness. This approach shifts the focus from extrinsic evaluation, which relies on downstream task performance, to the inherent properties of the data itself. Using this evaluation system, we analyze the experimental evaluations of representative generation methods for each modality and identify substantial deficiencies in current evaluation practices. Based on these findings, we offer concrete recommendations for the community to improve the evaluation of data generation. Finally, the framework outlines methodologies for the practical application of synthetic data across different modalities.

We present a framework for the automated measurement of responsible AI (RAI) metrics for large language models (LLMs) and associated products and services. Our framework for automatically measuring harms from LLMs builds on existing technical and sociotechnical expertise and leverages the capabilities of state-of-the-art LLMs, such as GPT-4. We use this framework to run through several case studies investigating how different LLMs may violate a range of RAI-related principles. The framework may be employed alongside domain-specific sociotechnical expertise to create measurements for new harm areas in the future. By implementing this framework, we aim to enable more advanced harm measurement efforts and further the responsible use of LLMs.

Security is becoming a pivotal point in cloud platforms. Several divisions, such as business organisations, health care, government, etc., have experienced cyber-attacks on their infrastructures. This research focuses on security issues within Continuous Integration and Deployment (CI/CD) pipelines in a cloud platform as a reaction to recent cyber breaches. This research proposes a blockchain-based solution to enhance CI/CD pipeline security. This research aims to develop a framework that leverages blockchain's distributed ledger technology and tamper-resistant features to improve CI/CD pipeline security. The goal is to emphasise secure software deployment by integrating threat modelling frameworks and adherence to coding standards. It also aims to employ tools to automate security testing to detect publicly disclosed vulnerabilities and flaws, such as an outdated version of Java Spring Framework, a JavaScript library from an unverified source, or a database library that allows SQL injection attacks in the deployed software through the framework.

External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of system access granted to auditors. Recent audits of state-of-the-art AI systems have primarily relied on black-box access, in which auditors can only query the system and observe its outputs. However, white-box access to the system's inner workings (e.g., weights, activations, gradients) allows an auditor to perform stronger attacks, more thoroughly interpret models, and conduct fine-tuning. Meanwhile, outside-the-box access to its training and deployment information (e.g., methodology, code, documentation, hyperparameters, data, deployment details, findings from internal evaluations) allows for auditors to scrutinize the development process and design more targeted evaluations. In this paper, we examine the limitations of black-box audits and the advantages of white- and outside-the-box audits. We also discuss technical, physical, and legal safeguards for performing these audits with minimal security risks. Given that different forms of access can lead to very different levels of evaluation, we conclude that (1) transparency regarding the access and methods used by auditors is necessary to properly interpret audit results, and (2) white- and outside-the-box access allow for substantially more scrutiny than black-box access alone.

Privacy policies are supposed to provide notice. But what if substantive information appears only where users skip it? We identify a structural pattern we call jurisdiction-siloed disclosure: information about data practices appearing in specific, actionable form only within regional compliance sections labeled "California Residents" or "EU/UK Users," while general sections use vague or qualified language for the same practices. Our audit of 123 major companies identifies 282 potential instances across 77 companies (62.6% of this purposive sample). A conservative estimate restricted to practice categories validated against OPP-115 human annotations finds 138 instances across 54 companies (44%); post-2018 categories central to our findings await independent validation. If users skip jurisdiction-labeled sections as information foraging theory predicts, users outside regulated jurisdictions would receive less specific information about practices affecting them--a transparency failure operating through document architecture rather than omission. We propose universal substantive disclosure: practices affecting all users should appear in the main policy body, with regional sections containing only procedural rights information. This standard finds support in analogous disclosure regimes (securities, truth-in-lending, nutritional labeling) where material information must reach all affected parties. Regulators could operationalize this through the FTC's "clear and conspicuous" standard and GDPR transparency principles. This work is hypothesis-generating: we establish that the structural pattern exists and ground the transparency concern in behavioral theory, but direct measurement of jurisdiction-specific section skipping remains the critical validation priority. We release our methodology and annotated dataset to enable replication.

Entity resolution (record linkage, microclustering) systems are notoriously difficult to evaluate. Looking for a needle in a haystack, traditional evaluation methods use sophisticated, application-specific sampling schemes to find matching pairs of records among an immense number of non-matches. We propose an alternative that facilitates the creation of representative, reusable benchmark data sets without necessitating complex sampling schemes. These benchmark data sets can then be used for model training and a variety of evaluation tasks. Specifically, we propose an entity-centric data labeling methodology that integrates with a unified framework for monitoring summary statistics, estimating key performance metrics such as cluster and pairwise precision and recall, and analyzing root causes for errors. We validate the framework in an application to inventor name disambiguation and through simulation studies. Software: https://github.com/OlivierBinette/er-evaluation/

The recent emergence and adoption of Machine Learning technology, and specifically of Large Language Models, has drawn attention to the need for systematic and transparent management of language data. This work proposes an approach to global language data governance that attempts to organize data management amongst stakeholders, values, and rights. Our proposal is informed by prior work on distributed governance that accounts for human values and grounded by an international research collaboration that brings together researchers and practitioners from 60 countries. The framework we present is a multi-party international governance structure focused on language data, and incorporating technical and organizational tools needed to support its work.

Harm reporting in Artificial Intelligence (AI) currently lacks a structured process for disclosing and addressing algorithmic flaws, relying largely on an ad-hoc approach. This contrasts sharply with the well-established Coordinated Vulnerability Disclosure (CVD) ecosystem in software security. While global efforts to establish frameworks for AI transparency and collaboration are underway, the unique challenges presented by machine learning (ML) models demand a specialized approach. To address this gap, we propose implementing a Coordinated Flaw Disclosure (CFD) framework tailored to the complexities of ML and AI issues. This paper reviews the evolution of ML disclosure practices, from ad hoc reporting to emerging participatory auditing methods, and compares them with cybersecurity norms. Our framework introduces innovations such as extended model cards, dynamic scope expansion, an independent adjudication panel, and an automated verification process. We also outline a forthcoming real-world pilot of CFD. We argue that CFD could significantly enhance public trust in AI systems. By balancing organizational and community interests, CFD aims to improve AI accountability in a rapidly evolving technological landscape.

Watermarking has emerged as a leading technical proposal for attributing generative AI content and is increasingly cited in global governance frameworks. This paper argues that current implementations risk serving as symbolic compliance rather than delivering effective oversight. We identify a growing gap between regulatory expectations and the technical limitations of existing watermarking schemes. Through analysis of policy proposals and industry practices, we show how incentive structures disincentivize robust, auditable deployments. To realign watermarking with governance goals, we propose a three-layer framework encompassing technical standards, audit infrastructure, and enforcement mechanisms. Without enforceable requirements and independent verification, watermarking will remain inadequate for accountability and ultimately undermine broader efforts in AI safety and regulation.

Developing foundation models in medical imaging requires continuous monitoring of downstream performance. Researchers are burdened with tracking numerous experiments, design choices, and their effects on performance, often relying on ad-hoc, manual workflows that are inherently slow and error-prone. We introduce EvalBlocks, a modular, plug-and-play framework for efficient evaluation of foundation models during development. Built on Snakemake, EvalBlocks supports seamless integration of new datasets, foundation models, aggregation methods, and evaluation strategies. All experiments and results are tracked centrally and are reproducible with a single command, while efficient caching and parallel execution enable scalable use on shared compute infrastructure. Demonstrated on five state-of-the-art foundation models and three medical imaging classification tasks, EvalBlocks streamlines model evaluation, enabling researchers to iterate faster and focus on model innovation rather than evaluation logistics. The framework is released as open source software at https://github.com/DIAGNijmegen/eval-blocks.

Foundation models, particularly those that incorporate Transformer architectures, have demonstrated exceptional performance in domains such as natural language processing and image processing. Adapting these models to structured data, like tables, however, introduces significant challenges. These difficulties are even more pronounced when addressing multi-table data linked via foreign key, which is prevalent in the enterprise realm and crucial for empowering business use cases. Despite its substantial impact, research focusing on such linked business tables within enterprise settings remains a significantly important yet underexplored domain. To address this, we introduce a curated dataset sourced from an Enterprise Resource Planning (ERP) system, featuring extensive linked tables. This dataset is specifically designed to support research endeavors in table representation learning. By providing access to authentic enterprise data, our goal is to potentially enhance the effectiveness and applicability of models for real-world business contexts.

New capabilities in foundation models are owed in large part to massive, widely-sourced, and under-documented training data collections. Existing practices in data collection have led to challenges in documenting data transparency, tracing authenticity, verifying consent, privacy, representation, bias, copyright infringement, and the overall development of ethical and trustworthy foundation models. In response, regulation is emphasizing the need for training data transparency to understand foundation models' limitations. Based on a large-scale analysis of the foundation model training data landscape and existing solutions, we identify the missing infrastructure to facilitate responsible foundation model development practices. We examine the current shortcomings of common tools for tracing data authenticity, consent, and documentation, and outline how policymakers, developers, and data creators can facilitate responsible foundation model development by adopting universal data provenance standards.

Software Quality Assurance (SQA) is critical for delivering reliable, secure, and efficient software products. The Software Quality Assurance Process aims to provide assurance that work products and processes comply with predefined provisions and plans. Recent advancements in Large Language Models (LLMs) present new opportunities to enhance existing SQA processes by automating tasks like requirement analysis, code review, test generation, and compliance checks. Simultaneously, established standards such as ISO/IEC 12207, ISO/IEC 25010, ISO/IEC 5055, ISO 9001/ISO/IEC 90003, CMMI, and TMM provide structured frameworks for ensuring robust quality practices. This paper surveys the intersection of LLM-based SQA methods and these recognized standards, highlighting how AI-driven solutions can augment traditional approaches while maintaining compliance and process maturity. We first review the foundational software quality standards and the technical fundamentals of LLMs in software engineering. Next, we explore various LLM-based SQA applications, including requirement validation, defect detection, test generation, and documentation maintenance. We then map these applications to key software quality frameworks, illustrating how LLMs can address specific requirements and metrics within each standard. Empirical case studies and open-source initiatives demonstrate the practical viability of these methods. At the same time, discussions on challenges (e.g., data privacy, model bias, explainability) underscore the need for deliberate governance and auditing. Finally, we propose future directions encompassing adaptive learning, privacy-focused deployments, multimodal analysis, and evolving standards for AI-driven software quality.

This research presents a framework for quantitative risk management in volatile markets, specifically focusing on expectile-based methodologies applied to the FTSE 100 index. Traditional risk measures such as Value-at-Risk (VaR) have demonstrated significant limitations during periods of market stress, as evidenced during the 2008 financial crisis and subsequent volatile periods. This study develops an advanced expectile-based framework that addresses the shortcomings of conventional quantile-based approaches by providing greater sensitivity to tail losses and improved stability in extreme market conditions. The research employs a dataset spanning two decades of FTSE 100 returns, incorporating periods of high volatility, market crashes, and recovery phases. Our methodology introduces novel mathematical formulations for expectile regression models, enhanced threshold determination techniques using time series analysis, and robust backtesting procedures. The empirical results demonstrate that expectile-based Value-at-Risk (EVaR) consistently outperforms traditional VaR measures across various confidence levels and market conditions. The framework exhibits superior performance during volatile periods, with reduced model risk and enhanced predictive accuracy. Furthermore, the study establishes practical implementation guidelines for financial institutions and provides evidence-based recommendations for regulatory compliance and portfolio management. The findings contribute significantly to the literature on financial risk management and offer practical tools for practitioners dealing with volatile market environments.

Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system's entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both from a technical and a social perspective. However, attaining truly trustworthy AI concerns a wider vision that comprises the trustworthiness of all processes and actors that are part of the system's life cycle, and considers previous aspects from different lenses. A more holistic vision contemplates four essential axes: the global principles for ethical use and development of AI-based systems, a philosophical take on AI ethics, a risk-based approach to AI regulation, and the mentioned pillars and requirements. The seven requirements (human agency and oversight; robustness and safety; privacy and data governance; transparency; diversity, non-discrimination and fairness; societal and environmental wellbeing; and accountability) are analyzed from a triple perspective: What each requirement for trustworthy AI is, Why it is needed, and How each requirement can be implemented in practice. On the other hand, a practical approach to implement trustworthy AI systems allows defining the concept of responsibility of AI-based systems facing the law, through a given auditing process. Therefore, a responsible AI system is the resulting notion we introduce in this work, and a concept of utmost necessity that can be realized through auditing processes, subject to the challenges posed by the use of regulatory sandboxes. Our multidisciplinary vision of trustworthy AI culminates in a debate on the diverging views published lately about the future of AI. Our reflections in this matter conclude that regulation is a key for reaching a consensus among these views, and that trustworthy and responsible AI systems will be crucial for the present and future of our society.

This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks. The goal is to balance general language proficiency with domain-specific skills. The methodology has three main components: 1) Carefully blending in-domain and general-purpose data during fine-tuning to achieve an optimal balance between general and specialized capabilities; 2) Designing a comprehensive evaluation framework with 45 questions tailored to assess performance on functionally relevant dimensions like reliability, consistency, and business impact; 3) Analyzing how model size and continual training influence metrics to guide efficient resource allocation during fine-tuning. The paper details the design, data collection, analytical techniques, and results validating the proposed frameworks. It aims to provide businesses and researchers with actionable insights on effectively adapting LLMs for specialized contexts. We also intend to make public the comprehensive evaluation framework, which includes the 45 tailored questions and their respective scoring guidelines, to foster transparency and collaboration in adapting LLMs for specialized tasks.

This paper introduces the open-source dataset WanJuanSiLu, designed to provide high-quality training corpora for low-resource languages, thereby advancing the research and development of multilingual models. To achieve this, we have developed a systematic data processing framework tailored for low-resource languages. This framework encompasses key stages such as data extraction, corpus cleaning, content deduplication, security filtering, quality evaluation, and theme classification. Through the implementation of this framework, we have significantly improved both the quality and security of the dataset, while maintaining its linguistic diversity. As of now, data for all five languages have been fully open-sourced. The dataset can be accessed at https://opendatalab.com/applyMultilingualCorpus, and GitHub repository is available at https://github.com/opendatalab/WanJuan3.0

Foundation model development attracts a rapidly expanding body of contributors, scientists, and applications. To help shape responsible development practices, we introduce the Foundation Model Development Cheatsheet: a growing collection of 250+ tools and resources spanning text, vision, and speech modalities. We draw on a large body of prior work to survey resources (e.g. software, documentation, frameworks, guides, and practical tools) that support informed data selection, processing, and understanding, precise and limitation-aware artifact documentation, efficient model training, advance awareness of the environmental impact from training, careful model evaluation of capabilities, risks, and claims, as well as responsible model release, licensing and deployment practices. We hope this curated collection of resources helps guide more responsible development. The process of curating this list, enabled us to review the AI development ecosystem, revealing what tools are critically missing, misused, or over-used in existing practices. We find that (i) tools for data sourcing, model evaluation, and monitoring are critically under-serving ethical and real-world needs, (ii) evaluations for model safety, capabilities, and environmental impact all lack reproducibility and transparency, (iii) text and particularly English-centric analyses continue to dominate over multilingual and multi-modal analyses, and (iv) evaluation of systems, rather than just models, is needed so that capabilities and impact are assessed in context.

The global trade in electronic and electrical goods is complicated by the challenge of identifying e-waste, which is often misclassified to evade regulations. Traditional analysis methods struggle to discern the underlying patterns of this illicit trade within vast datasets. This research proposes and validates a robust, data-driven framework to segment products and identify goods exhibiting an anomalous "waste signature" a trade pattern defined by a clear 'inverse price-volume'. The core of the framework is an Outlier-Aware Segmentation method, an iterative K-Means approach that first isolates extreme outliers to prevent data skewing and then re-clusters the remaining products to reveal subtle market segments. To quantify risk, a "Waste Score" is developed using a Logistic Regression model that identifies products whose trade signatures are statistically similar to scrap. The findings reveal a consistent four-tier market hierarchy in both Malaysian and global datasets. A key pattern emerged from a comparative analysis: Malaysia's market structure is defined by high-volume bulk commodities, whereas the global market is shaped by high-value capital goods, indicating a unique national specialization. The framework successfully flags finished goods, such as electric generators (HS 8502), that are traded like scrap, providing a targeted list for regulatory scrutiny.

Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities--popular text, speech, and video datasets--from their detailed sourcing trends and use restrictions to their geographical and linguistic representation. Our manual analysis covers nearly 4000 public datasets between 1990-2024, spanning 608 languages, 798 sources, 659 organizations, and 67 countries. We find that multimodal machine learning applications have overwhelmingly turned to web-crawled, synthetic, and social media platforms, such as YouTube, for their training sets, eclipsing all other sources since 2019. Secondly, tracing the chain of dataset derivations we find that while less than 33% of datasets are restrictively licensed, over 80% of the source content in widely-used text, speech, and video datasets, carry non-commercial restrictions. Finally, counter to the rising number of languages and geographies represented in public AI training datasets, our audit demonstrates measures of relative geographical and multilingual representation have failed to significantly improve their coverage since 2013. We believe the breadth of our audit enables us to empirically examine trends in data sourcing, restrictions, and Western-centricity at an ecosystem-level, and that visibility into these questions are essential to progress in responsible AI. As a contribution to ongoing improvements in dataset transparency and responsible use, we release our entire multimodal audit, allowing practitioners to trace data provenance across text, speech, and video.

Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are limited by static pretraining, short context windows, and challenges in processing heterogeneous data formats. Conventional Retrieval-Augmented Generation (RAG) frameworks address some of these gaps but often struggle with structured and semi-structured data. This work proposes an advanced RAG framework that combines hybrid retrieval strategies using dense embeddings (all-mpnet-base-v2) and BM25, enhanced by metadata-aware filtering with SpaCy NER and cross-encoder reranking. The framework applies semantic chunking to maintain textual coherence and retains tabular data structures to preserve row-column integrity. Quantized indexing optimizes retrieval efficiency, while human-in-the-loop feedback and conversation memory improve adaptability. Experiments on enterprise datasets show notable improvements: Precision@5 increased by 15 percent (90 versus 75), Recall@5 by 13 percent (87 versus 74), and Mean Reciprocal Rank by 16 percent (0.85 versus 0.69). Qualitative evaluations show higher scores in Faithfulness (4.6 versus 3.0), Completeness (4.2 versus 2.5), and Relevance (4.5 versus 3.2) on a 5-point Likert scale. These results demonstrate the framework's effectiveness in delivering accurate, comprehensive, and contextually relevant responses for enterprise tasks. Future work includes extending to multimodal data and integrating agent-based retrieval. The source code will be released at https://github.com/CheerlaChandana/Enterprise-Chatbot

The quality of underlying training data is very crucial for building performant machine learning models with wider generalizabilty. However, current machine learning (ML) tools lack streamlined processes for improving the data quality. So, getting data quality insights and iteratively pruning the errors to obtain a dataset which is most representative of downstream use cases is still an ad-hoc manual process. Our work addresses this data tooling gap, required to build improved ML workflows purely through data-centric techniques. More specifically, we introduce a systematic framework for (1) finding noisy or mislabelled samples in the dataset and, (2) identifying the most informative samples, which when included in training would provide maximal model performance lift. We demonstrate the efficacy of our framework on public as well as private enterprise datasets of two Fortune 500 companies, and are confident this work will form the basis for ML teams to perform more intelligent data discovery and pruning.

The Model Context Protocol (MCP) is an emerging standard designed to enable seamless interaction between Large Language Model (LLM) applications and external tools or resources. Within a short period, thousands of MCP services have already been developed and deployed. However, the client-server integration architecture inherent in MCP may expand the attack surface against LLM Agent systems, introducing new vulnerabilities that allow attackers to exploit by designing malicious MCP servers. In this paper, we present the first systematic study of attack vectors targeting the MCP ecosystem. Our analysis identifies four categories of attacks, i.e., Tool Poisoning Attacks, Puppet Attacks, Rug Pull Attacks, and Exploitation via Malicious External Resources. To evaluate the feasibility of these attacks, we conduct experiments following the typical steps of launching an attack through malicious MCP servers: upload-download-attack. Specifically, we first construct malicious MCP servers and successfully upload them to three widely used MCP aggregation platforms. The results indicate that current audit mechanisms are insufficient to identify and prevent the proposed attack methods. Next, through a user study and interview with 20 participants, we demonstrate that users struggle to identify malicious MCP servers and often unknowingly install them from aggregator platforms. Finally, we demonstrate that these attacks can trigger harmful behaviors within the user's local environment-such as accessing private files or controlling devices to transfer digital assets-by deploying a proof-of-concept (PoC) framework against five leading LLMs. Additionally, based on interview results, we discuss four key challenges faced by the current security ecosystem surrounding MCP servers. These findings underscore the urgent need for robust security mechanisms to defend against malicious MCP servers.

Randomized controlled trials (RCTs) are the benchmark for causal inference, yet field implementation can deviate. We here present a remote audit - a design-based, preregistrable diagnostic that uses only pre-treatment satellite imagery to test whether assignment is independent of local conditions. The conditional randomization test of the remote audit evaluates whether treatment assignment is more predictable from pre-treatment satellite features than expected under the experiment's registered mechanism, providing a finite-sample valid, design-based diagnostic that requires no parametric assumptions. The procedure is finite-sample valid, honors blocks and clusters, and controls multiplicity across image models and resolutions via a max-statistic. We illustrate with two RCTs: Uganda's Youth Opportunities Program, where the audit corroborates randomization and flags selection and missing-data risks; and a school-based trial in Bangladesh, where assignment is highly predictable from pre-treatment features relative to the stated design, consistent with independent concerns about irregularities. Remote audits complement balance tests, lower early-stage costs, and enable rapid design checks when baseline surveys are expensive or infeasible.

Organizations of all sizes, across all industries and domains are leveraging artificial intelligence (AI) technologies to solve some of their biggest challenges around operations, customer experience, and much more. However, due to the probabilistic nature of AI, the risks associated with it are far greater than traditional technologies. Research has shown that these risks can range anywhere from regulatory, compliance, reputational, and user trust, to financial and even societal risks. Depending on the nature and size of the organization, AI technologies can pose a significant risk, if not used in a responsible way. This position paper seeks to present a brief introduction to AI governance, which is a framework designed to oversee the responsible use of AI with the goal of preventing and mitigating risks. Having such a framework will not only manage risks but also gain maximum value out of AI projects and develop consistency for organization-wide adoption of AI.

Evaluating the quality of synthetic data remains a key challenge for ensuring privacy and utility in data-driven research. In this work, we present an evaluation framework that quantifies how well synthetic data replicates original distributional properties while ensuring privacy. The proposed approach employs a holdout-based benchmarking strategy that facilitates quantitative assessment through low- and high-dimensional distribution comparisons, embedding-based similarity measures, and nearest-neighbor distance metrics. The framework supports various data types and structures, including sequential and contextual information, and enables interpretable quality diagnostics through a set of standardized metrics. These contributions aim to support reproducibility and methodological consistency in benchmarking of synthetic data generation techniques. The code of the framework is available at https://github.com/mostly-ai/mostlyai-qa.

Enterprise Resource Planning (ERP) systems serve as the digital backbone of modern financial institutions, yet they continue to rely on static, rule-based workflows that limit adaptability, scalability, and intelligence. As business operations grow more complex and data-rich, conventional ERP platforms struggle to integrate structured and unstructured data in real time and to accommodate dynamic, cross-functional workflows. In this paper, we present the first AI-native, agent-based framework for ERP systems, introducing a novel architecture of Generative Business Process AI Agents (GBPAs) that bring autonomy, reasoning, and dynamic optimization to enterprise workflows. The proposed system integrates generative AI with business process modeling and multi-agent orchestration, enabling end-to-end automation of complex tasks such as budget planning, financial reporting, and wire transfer processing. Unlike traditional workflow engines, GBPAs interpret user intent, synthesize workflows in real time, and coordinate specialized sub-agents for modular task execution. We validate the framework through case studies in bank wire transfers and employee reimbursements, two representative financial workflows with distinct complexity and data modalities. Results show that GBPAs achieve up to 40% reduction in processing time, 94% drop in error rate, and improved regulatory compliance by enabling parallelism, risk control insertion, and semantic reasoning. These findings highlight the potential of GBPAs to bridge the gap between generative AI capabilities and enterprise-grade automation, laying the groundwork for the next generation of intelligent ERP systems.

As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable controls. We introduce a regulatory machine learning framework that converts unstructured design artifacts (like PRDs, TDDs, and code) into verifiable runtime guardrails. Our Policy as Prompt method reads these documents and risk controls to build a source-linked policy tree. This tree is then compiled into lightweight, prompt-based classifiers for real-time runtime monitoring. The system is built to enforce least privilege and data minimization. For conformity assessment, it provides complete provenance, traceability, and audit logging, all integrated with a human-in-the-loop review process. Evaluations show our system reduces prompt-injection risk, blocks out-of-scope requests, and limits toxic outputs. It also generates auditable rationales aligned with AI governance frameworks. By treating policies as executable prompts (a policy-as-code for agents), this approach enables secure-by-design deployment, continuous compliance, and scalable AI safety and AI security assurance for regulatable ML.

We employ an audit design to investigate biases in state-of-the-art large language models, including GPT-4. In our study, we prompt the models for advice involving a named individual across a variety of scenarios, such as during car purchase negotiations or election outcome predictions. We find that the advice systematically disadvantages names that are commonly associated with racial minorities and women. Names associated with Black women receive the least advantageous outcomes. The biases are consistent across 42 prompt templates and several models, indicating a systemic issue rather than isolated incidents. While providing numerical, decision-relevant anchors in the prompt can successfully counteract the biases, qualitative details have inconsistent effects and may even increase disparities. Our findings underscore the importance of conducting audits at the point of LLM deployment and implementation to mitigate their potential for harm against marginalized communities.

Supply chain operations traditionally involve a variety of complex decision making problems. Over the last few decades, supply chains greatly benefited from advances in computation, which allowed the transition from manual processing to automation and cost-effective optimization. Nonetheless, business operators still need to spend substantial efforts in explaining and interpreting the optimization outcomes to stakeholders. Motivated by the recent advances in Large Language Models (LLMs), we study how this disruptive technology can help bridge the gap between supply chain automation and human comprehension and trust thereof. We design -- a framework that accepts as input queries in plain text, and outputs insights about the underlying optimization outcomes. Our framework does not forgo the state-of-the-art combinatorial optimization technology, but rather leverages it to quantitatively answer what-if scenarios (e.g., how would the cost change if we used supplier B instead of supplier A for a given demand?). Importantly, our design does not require sending proprietary data over to LLMs, which can be a privacy concern in some circumstances. We demonstrate the effectiveness of our framework on a real server placement scenario within Microsoft's cloud supply chain. Along the way, we develop a general evaluation benchmark, which can be used to evaluate the accuracy of the LLM output in other scenarios.

Cardiac ultrasound (US) scanning is a commonly used techniques in cardiology to diagnose the health of the heart and its proper functioning. Therefore, it is necessary to consider ways to automate these tasks and assist medical professionals in classifying and assessing cardiac US images. Machine learning (ML) techniques are regarded as a prominent solution due to their success in numerous applications aimed at enhancing the medical field, including addressing the shortage of echography technicians. However, the limited availability of medical data presents a significant barrier to applying ML in cardiology, particularly regarding US images of the heart. This paper addresses this challenge by introducing the first open graded dataset for Cardiac Assessment and ClassificaTion of UltraSound (CACTUS), which is available online. This dataset contains images obtained from scanning a CAE Blue Phantom and representing various heart views and different quality levels, exceeding the conventional cardiac views typically found in the literature. Additionally, the paper introduces a Deep Learning (DL) framework consisting of two main components. The first component classifies cardiac US images based on the heart view using a Convolutional Neural Network (CNN). The second component uses Transfer Learning (TL) to fine-tune the knowledge from the first component and create a model for grading and assessing cardiac images. The framework demonstrates high performance in both classification and grading, achieving up to 99.43% accuracy and as low as 0.3067 error, respectively. To showcase its robustness, the framework is further fine-tuned using new images representing additional cardiac views and compared to several other state-of-the-art architectures. The framework's outcomes and performance in handling real-time scans were also assessed using a questionnaire answered by cardiac experts.

Enterprise ERP systems managing hundreds of thousands of employee records face critical data quality challenges when human resources departments perform decentralized manual entry across multiple languages. We present an end-to-end pipeline combining automated data cleaning with LLM-driven SQL query generation, deployed on a production system managing 240,000 employee records over six months. The system operates in two integrated stages: a multi-stage cleaning pipeline that performs translation normalization, spelling correction, and entity deduplication during periodic synchronization from Microsoft SQL Server to PostgreSQL; and a retrieval-augmented generation framework powered by GPT-4o that translates natural-language questions in Turkish, Russian, and English into validated SQL queries. The query engine employs LangChain orchestration, FAISS vector similarity search, and few-shot learning with 500+ validated examples. Our evaluation demonstrates 92.5% query validity, 95.1% schema compliance, and 90.7\% semantic accuracy on 2,847 production queries. The system reduces query turnaround time from 2.3 days to under 5 seconds while maintaining 99.2% uptime, with GPT-4o achieving 46% lower latency and 68% cost reduction versus GPT-3.5. This modular architecture provides a reproducible framework for AI-native enterprise data governance, demonstrating real-world viability at enterprise scale with 4.3/5.0 user satisfaction.

Artificial intelligence (AI) systems will increasingly be used to cause harm as they grow more capable. In fact, AI systems are already starting to be used to automate fraudulent activities, violate human rights, create harmful fake images, and identify dangerous toxins. To prevent some misuses of AI, we argue that targeted interventions on certain capabilities will be warranted. These restrictions may include controlling who can access certain types of AI models, what they can be used for, whether outputs are filtered or can be traced back to their user, and the resources needed to develop them. We also contend that some restrictions on non-AI capabilities needed to cause harm will be required. Though capability restrictions risk reducing use more than misuse (facing an unfavorable Misuse-Use Tradeoff), we argue that interventions on capabilities are warranted when other interventions are insufficient, the potential harm from misuse is high, and there are targeted ways to intervene on capabilities. We provide a taxonomy of interventions that can reduce AI misuse, focusing on the specific steps required for a misuse to cause harm (the Misuse Chain), and a framework to determine if an intervention is warranted. We apply this reasoning to three examples: predicting novel toxins, creating harmful images, and automating spear phishing campaigns.

We present ExpliCIT-QA, a system that extends our previous MRT approach for tabular question answering into a multimodal pipeline capable of handling complex table images and providing explainable answers. ExpliCIT-QA follows a modular design, consisting of: (1) Multimodal Table Understanding, which uses a Chain-of-Thought approach to extract and transform content from table images; (2) Language-based Reasoning, where a step-by-step explanation in natural language is generated to solve the problem; (3) Automatic Code Generation, where Python/Pandas scripts are created based on the reasoning steps, with feedback for handling errors; (4) Code Execution to compute the final answer; and (5) Natural Language Explanation that describes how the answer was computed. The system is built for transparency and auditability: all intermediate outputs, parsed tables, reasoning steps, generated code, and final answers are available for inspection. This strategy works towards closing the explainability gap in end-to-end TableVQA systems. We evaluated ExpliCIT-QA on the TableVQA-Bench benchmark, comparing it with existing baselines. We demonstrated improvements in interpretability and transparency, which open the door for applications in sensitive domains like finance and healthcare where auditing results are critical.

Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the justification production and uncover the nuanced limitations of LLMs in fact-checking. In this work, we introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities. Leveraging importance sampling principles and multi-agent collaboration, FACT-AUDIT generates adaptive and scalable datasets, performs iterative model-centric evaluations, and updates assessments based on model-specific responses. By incorporating justification production alongside verdict prediction, this framework provides a comprehensive and evolving audit of LLMs' factual reasoning capabilities, to investigate their trustworthiness. Extensive experiments demonstrate that FACT-AUDIT effectively differentiates among state-of-the-art LLMs, providing valuable insights into model strengths and limitations in model-centric fact-checking analysis.

Annual Reports of publicly listed companies contain vital information about their financial health which can help assess the potential impact on Stock price of the firm. These reports are comprehensive in nature, going up to, and sometimes exceeding, 100 pages. Analysing these reports is cumbersome even for a single firm, let alone the whole universe of firms that exist. Over the years, financial experts have become proficient in extracting valuable information from these documents relatively quickly. However, this requires years of practice and experience. This paper aims to simplify the process of assessing Annual Reports of all the firms by leveraging the capabilities of Large Language Models (LLMs). The insights generated by the LLM are compiled in a Quant styled dataset and augmented by historical stock price data. A Machine Learning model is then trained with LLM outputs as features. The walkforward test results show promising outperformance wrt S&P500 returns. This paper intends to provide a framework for future work in this direction. To facilitate this, the code has been released as open source.

The development of audio foundation models has accelerated rapidly since the emergence of GPT-4o. However, the lack of comprehensive evaluation has become a critical bottleneck for further progress in the field, particularly in audio generation. Current audio evaluation faces three major challenges: (1) audio evaluation lacks a unified framework, with datasets and code scattered across various sources, hindering fair and efficient cross-model comparison;(2) audio codecs, as a key component of audio foundation models, lack a widely accepted and holistic evaluation methodology; (3) existing speech benchmarks are heavily reliant on English, making it challenging to objectively assess models' performance on Chinese. To address the first issue, we introduce UltraEval-Audio, a unified evaluation framework for audio foundation models, specifically designed for both audio understanding and generation tasks. UltraEval-Audio features a modular architecture, supporting 10 languages and 14 core task categories, while seamlessly integrating 24 mainstream models and 36 authoritative benchmarks. To enhance research efficiency, the framework provides a one-command evaluation feature, accompanied by real-time public leaderboards. For the second challenge, UltraEval-Audio adopts a novel comprehensive evaluation scheme for audio codecs, evaluating performance across three key dimensions: semantic accuracy, timbre fidelity, and acoustic quality. To address the third issue, we propose two new Chinese benchmarks, SpeechCMMLU and SpeechHSK, designed to assess Chinese knowledge proficiency and language fluency. We wish that UltraEval-Audio will provide both academia and industry with a transparent, efficient, and fair platform for comparison of audio models. Our code, benchmarks, and leaderboards are available at https://github.com/OpenBMB/UltraEval-Audio.

Invoices and receipts submitted by employees are visually rich documents (VRDs) with textual, visual and layout information. To protect against the risk of fraud and abuse, it is crucial for organizations to efficiently extract desired information from submitted receipts. This helps in the assessment of key factors such as appropriateness of the expense claim, adherence to spending and transaction policies, the validity of the receipt, as well as downstream anomaly detection at various levels. These documents are heterogeneous, with multiple formats and languages, uploaded with different image qualities, and often do not contain ground truth labels for the efficient training of models. In this paper we propose Task Aware Instruction-based Labelling (TAIL), a method for synthetic label generation in VRD corpuses without labels, and fine-tune a multimodal Visually Rich Document Understanding Model (VRDU) on TAIL labels using response-based knowledge distillation without using the teacher model's weights or training dataset to conditionally generate annotations in the appropriate format. Using a benchmark external dataset where ground truth labels are available, we demonstrate conditions under which our approach performs at par with Claude 3 Sonnet through empirical studies. We then show that the resulting model performs at par or better on the internal expense documents of a large multinational organization than state-of-the-art LMM (large multimodal model) Claude 3 Sonnet while being 85% less costly and ~5X faster, and outperforms layout-aware baselines by more than 10% in Average Normalized Levenshtein Similarity (ANLS) scores due to its ability to reason and extract information from rare formats. Finally, we illustrate the usage of our approach in overpayment prevention.

The popularity and widespread use of pruning and quantization is driven by the severe resource constraints of deploying deep neural networks to environments with strict latency, memory and energy requirements. These techniques achieve high levels of compression with negligible impact on top-line metrics (top-1 and top-5 accuracy). However, overall accuracy hides disproportionately high errors on a small subset of examples; we call this subset Compression Identified Exemplars (CIE). We further establish that for CIE examples, compression amplifies existing algorithmic bias. Pruning disproportionately impacts performance on underrepresented features, which often coincides with considerations of fairness. Given that CIE is a relatively small subset but a great contributor of error in the model, we propose its use as a human-in-the-loop auditing tool to surface a tractable subset of the dataset for further inspection or annotation by a domain expert. We provide qualitative and quantitative support that CIE surfaces the most challenging examples in the data distribution for human-in-the-loop auditing.

Code auditing is the process of reviewing code with the aim of identifying bugs. Large Language Models (LLMs) have demonstrated promising capabilities for this task without requiring compilation, while also supporting user-friendly customization. However, auditing a code repository with LLMs poses significant challenges: limited context windows and hallucinations can degrade the quality of bug reports, and analyzing large-scale repositories incurs substantial time and token costs, hindering efficiency and scalability. This work introduces an LLM-based agent, RepoAudit, designed to perform autonomous repository-level code auditing. Equipped with agent memory, RepoAudit explores the codebase on demand by analyzing data-flow facts along feasible program paths within individual functions. It further incorporates a validator module to mitigate hallucinations by verifying data-flow facts and checking the satisfiability of path conditions associated with potential bugs, thereby reducing false positives. RepoAudit detects 40 true bugs across 15 real-world benchmark projects with a precision of 78.43%, requiring on average only 0.44 hours and $2.54 per project. Also, it detects 185 new bugs in high-profile projects, among which 174 have been confirmed or fixed. We have open-sourced RepoAudit at https://github.com/PurCL/RepoAudit.

The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available, their customization capabilities for specific tasks and datasets are often complex for different users. In this study, we introduce the LLMeBench framework. Initially developed to evaluate Arabic NLP tasks using OpenAI's GPT and BLOOM models; it can be seamlessly customized for any NLP task and model, regardless of language. The framework also features zero- and few-shot learning settings. A new custom dataset can be added in less than 10 minutes, and users can use their own model API keys to evaluate the task at hand. The developed framework has been already tested on 31 unique NLP tasks using 53 publicly available datasets within 90 experimental setups, involving approximately 296K data points. We plan to open-source the framework for the community (https://github.com/qcri/LLMeBench/). A video demonstrating the framework is available online (https://youtu.be/FkQn4UjYA0s).

The scholarly publishing ecosystem faces a dual crisis of unmanageable submission volumes and unregulated AI, creating an urgent need for new governance models to safeguard scientific integrity. The traditional human-only peer review regime lacks a scalable, objective benchmark, making editorial processes opaque and difficult to audit. Here we investigate a deterministic simulation framework that provides the first stable, evidence-based standard for evaluating AI-generated peer review reports. Analyzing 352 peer-review simulation reports, we identify consistent system state indicators that demonstrate its reliability. First, the system is able to simulate calibrated editorial judgment, with 'Revise' decisions consistently forming the majority outcome (>50%) across all disciplines, while 'Reject' rates dynamically adapt to field-specific norms, rising to 45% in Health Sciences. Second, it maintains unwavering procedural integrity, enforcing a stable 29% evidence-anchoring compliance rate that remains invariant across diverse review tasks and scientific domains. These findings demonstrate a system that is predictably rule-bound, mitigating the stochasticity of generative AI. For the scientific community, this provides a transparent tool to ensure fairness; for publishing strategists, it offers a scalable instrument for auditing workflows, managing integrity risks, and implementing evidence-based governance. The framework repositions AI as an essential component of institutional accountability, providing the critical infrastructure to maintain trust in scholarly communication.

Personalized financial advice requires consideration of user goals, constraints, risk tolerance, and jurisdiction. Prior LLM work has focused on support systems for investors and financial planners. Simultaneously, numerous recent studies examine broader personal finance tasks, including budgeting, debt management, retirement, and estate planning, through agentic pipelines that incur high maintenance costs, yielding less than 25% of their expected financial returns. In this study, we introduce a novel and reproducible framework that integrates relevant financial context with behavioral finance studies to construct supervision data for end-to-end advisors. Using this framework, we create a 19k sample reasoning dataset and conduct a comprehensive fine-tuning of the Qwen-3-8B model on the dataset. Through a held-out test split and a blind LLM-jury study, we demonstrate that through careful data curation and behavioral integration, our 8B model achieves performance comparable to significantly larger baselines (14-32B parameters) across factual accuracy, fluency, and personalization metrics while incurring 80% lower costs than the larger counterparts.

Electronic Health Records (EHRs) are integral for storing comprehensive patient medical records, combining structured data (e.g., medications) with detailed clinical notes (e.g., physician notes). These elements are essential for straightforward data retrieval and provide deep, contextual insights into patient care. However, they often suffer from discrepancies due to unintuitive EHR system designs and human errors, posing serious risks to patient safety. To address this, we developed EHRCon, a new dataset and task specifically designed to ensure data consistency between structured tables and unstructured notes in EHRs. EHRCon was crafted in collaboration with healthcare professionals using the MIMIC-III EHR dataset, and includes manual annotations of 3,943 entities across 105 clinical notes checked against database entries for consistency. EHRCon has two versions, one using the original MIMIC-III schema, and another using the OMOP CDM schema, in order to increase its applicability and generalizability. Furthermore, leveraging the capabilities of large language models, we introduce CheckEHR, a novel framework for verifying the consistency between clinical notes and database tables. CheckEHR utilizes an eight-stage process and shows promising results in both few-shot and zero-shot settings. The code is available at https://github.com/dustn1259/EHRCon.

Automating legal document drafting can significantly enhance efficiency, reduce manual effort, and streamline legal workflows. While prior research has explored tasks such as judgment prediction and case summarization, the structured generation of private legal documents in the Indian legal domain remains largely unaddressed. To bridge this gap, we introduce VidhikDastaavej, a novel, anonymized dataset of private legal documents, and develop NyayaShilp, a fine-tuned legal document generation model specifically adapted to Indian legal texts. We propose a Model-Agnostic Wrapper (MAW), a two-step framework that first generates structured section titles and then iteratively produces content while leveraging retrieval-based mechanisms to ensure coherence and factual accuracy. We benchmark multiple open-source LLMs, including instruction-tuned and domain-adapted versions, alongside proprietary models for comparison. Our findings indicate that while direct fine-tuning on small datasets does not always yield improvements, our structured wrapper significantly enhances coherence, factual adherence, and overall document quality while mitigating hallucinations. To ensure real-world applicability, we developed a Human-in-the-Loop (HITL) Document Generation System, an interactive user interface that enables users to specify document types, refine section details, and generate structured legal drafts. This tool allows legal professionals and researchers to generate, validate, and refine AI-generated legal documents efficiently. Extensive evaluations, including expert assessments, confirm that our framework achieves high reliability in structured legal drafting. This research establishes a scalable and adaptable foundation for AI-assisted legal drafting in India, offering an effective approach to structured legal document generation.

Fact-checking plays a crucial role in combating misinformation. Existing methods using large language models (LLMs) for claim decomposition face two key limitations: (1) insufficient decomposition, introducing unnecessary complexity to the verification process, and (2) ambiguity of mentions, leading to incorrect verification results. To address these challenges, we suggest introducing a claim graph consisting of triplets to address the insufficient decomposition problem and reduce mention ambiguity through graph structure. Based on this core idea, we propose a graph-based framework, GraphFC, for fact-checking. The framework features three key components: graph construction, which builds both claim and evidence graphs; graph-guided planning, which prioritizes the triplet verification order; and graph-guided checking, which verifies the triples one by one between claim and evidence graphs. Extensive experiments show that GraphFC enables fine-grained decomposition while resolving referential ambiguities through relational constraints, achieving state-of-the-art performance across three datasets.

The successes of foundation models such as ChatGPT and AlphaFold have spurred significant interest in building similar models for electronic medical records (EMRs) to improve patient care and hospital operations. However, recent hype has obscured critical gaps in our understanding of these models' capabilities. We review over 80 foundation models trained on non-imaging EMR data (i.e. clinical text and/or structured data) and create a taxonomy delineating their architectures, training data, and potential use cases. We find that most models are trained on small, narrowly-scoped clinical datasets (e.g. MIMIC-III) or broad, public biomedical corpora (e.g. PubMed) and are evaluated on tasks that do not provide meaningful insights on their usefulness to health systems. In light of these findings, we propose an improved evaluation framework for measuring the benefits of clinical foundation models that is more closely grounded to metrics that matter in healthcare.

Even though machine learning (ML) pipelines affect an increasing array of stakeholders, there is little work on how input from stakeholders is recorded and incorporated. We propose FeedbackLogs, addenda to existing documentation of ML pipelines, to track the input of multiple stakeholders. Each log records important details about the feedback collection process, the feedback itself, and how the feedback is used to update the ML pipeline. In this paper, we introduce and formalise a process for collecting a FeedbackLog. We also provide concrete use cases where FeedbackLogs can be employed as evidence for algorithmic auditing and as a tool to record updates based on stakeholder feedback.

Financial institutions deploy Large Language Models (LLMs) for reconciliations, regulatory reporting, and client communications, but nondeterministic outputs (output drift) undermine auditability and trust. We quantify drift across five model architectures (7B-120B parameters) on regulated financial tasks, revealing a stark inverse relationship: smaller models (Granite-3-8B, Qwen2.5-7B) achieve 100% output consistency at T=0.0, while GPT-OSS-120B exhibits only 12.5% consistency (95% CI: 3.5-36.0%) regardless of configuration (p<0.0001, Fisher's exact test). This finding challenges conventional assumptions that larger models are universally superior for production deployment. Our contributions include: (i) a finance-calibrated deterministic test harness combining greedy decoding (T=0.0), fixed seeds, and SEC 10-K structure-aware retrieval ordering; (ii) task-specific invariant checking for RAG, JSON, and SQL outputs using finance-calibrated materiality thresholds (plus or minus 5%) and SEC citation validation; (iii) a three-tier model classification system enabling risk-appropriate deployment decisions; and (iv) an audit-ready attestation system with dual-provider validation. We evaluated five models (Qwen2.5-7B via Ollama, Granite-3-8B via IBM watsonx.ai, Llama-3.3-70B, Mistral-Medium-2505, and GPT-OSS-120B) across three regulated financial tasks. Across 480 runs (n=16 per condition), structured tasks (SQL) remain stable even at T=0.2, while RAG tasks show drift (25-75%), revealing task-dependent sensitivity. Cross-provider validation confirms deterministic behavior transfers between local and cloud deployments. We map our framework to Financial Stability Board (FSB), Bank for International Settlements (BIS), and Commodity Futures Trading Commission (CFTC) requirements, demonstrating practical pathways for compliance-ready AI deployments.

Ensuring that Software Requirements Specifications (SRS) align with higher-level organizational or national requirements is vital, particularly in regulated environments such as finance and aerospace. In these domains, maintaining consistency, adhering to regulatory frameworks, minimizing errors, and meeting critical expectations are essential for the reliable functioning of systems. The widespread adoption of large language models (LLMs) highlights their immense potential, yet there remains considerable scope for improvement in retrieving relevant information and enhancing reasoning capabilities. This study demonstrates that integrating a robust Graph-RAG framework with advanced prompt engineering techniques, such as Chain of Thought and Tree of Thought, can significantly enhance performance. Compared to baseline RAG methods and simple prompting strategies, this approach delivers more accurate and context-aware results. While this method demonstrates significant improvements in performance, it comes with challenges. It is both costly and more complex to implement across diverse contexts, requiring careful adaptation to specific scenarios. Additionally, its effectiveness heavily relies on having complete and accurate input data, which may not always be readily available, posing further limitations to its scalability and practicality.

Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning. While prior MIA research has primarily focused on performance metrics such as AUC, accuracy, and TPR@low FPR - either by developing new methods to enhance these metrics or using them to evaluate privacy solutions - we found that it overlooks the disparities among different attacks. These disparities, both between distinct attack methods and between multiple instantiations of the same method, have crucial implications for the reliability and completeness of MIAs as privacy evaluation tools. In this paper, we systematically investigate these disparities through a novel framework based on coverage and stability analysis. Extensive experiments reveal significant disparities in MIAs, their potential causes, and their broader implications for privacy evaluation. To address these challenges, we propose an ensemble framework with three distinct strategies to harness the strengths of state-of-the-art MIAs while accounting for their disparities. This framework not only enables the construction of more powerful attacks but also provides a more robust and comprehensive methodology for privacy evaluation.

As post-training techniques evolve, large language models (LLMs) are increasingly augmented with structured multi-step reasoning abilities, often optimized through reinforcement learning. These reasoning-enhanced models outperform standard LLMs on complex tasks and now underpin many commercial LLM APIs. However, to protect proprietary behavior and reduce verbosity, providers typically conceal the reasoning traces while returning only the final answer. This opacity introduces a critical transparency gap: users are billed for invisible reasoning tokens, which often account for the majority of the cost, yet have no means to verify their authenticity. This opens the door to token count inflation, where providers may overreport token usage or inject synthetic, low-effort tokens to inflate charges. To address this issue, we propose CoIn, a verification framework that audits both the quantity and semantic validity of hidden tokens. CoIn constructs a verifiable hash tree from token embedding fingerprints to check token counts, and uses embedding-based relevance matching to detect fabricated reasoning content. Experiments demonstrate that CoIn, when deployed as a trusted third-party auditor, can effectively detect token count inflation with a success rate reaching up to 94.7%, showing the strong ability to restore billing transparency in opaque LLM services. The dataset and code are available at https://github.com/CASE-Lab-UMD/LLM-Auditing-CoIn.

Multi-hop reasoning over financial disclosures is often a retrieval problem before it becomes a reasoning or generation problem: relevant facts are dispersed across sections, filings, companies, and years, and LLMs often expend excessive tokens navigating noisy context. Without precise Knowledge Graph (KG)-guided selection of relevant context, even strong reasoning models either fail to answer or consume excessive tokens, whereas KG-linked evidence enables models to focus their reasoning on composing already retrieved facts. We present FinReflectKG - MultiHop, a benchmark built on FinReflectKG, a temporally indexed financial KG that links audited triples to source chunks from S&P 100 filings (2022-2024). Mining frequent 2-3 hop subgraph patterns across sectors (via GICS taxonomy), we generate financial analyst style questions with exact supporting evidence from the KG. A two-phase pipeline first creates QA pairs via pattern-specific prompts, followed by a multi-criteria quality control evaluation to ensure QA validity. We then evaluate three controlled retrieval scenarios: (S1) precise KG-linked paths; (S2) text-only page windows centered on relevant text spans; and (S3) relevant page windows with randomizations and distractors. Across both reasoning and non-reasoning models, KG-guided precise retrieval yields substantial gains on the FinReflectKG - MultiHop QA benchmark dataset, boosting correctness scores by approximately 24 percent while reducing token utilization by approximately 84.5 percent compared to the page window setting, which reflects the traditional vector retrieval paradigm. Spanning intra-document, inter-year, and cross-company scopes, our work underscores the pivotal role of knowledge graphs in efficiently connecting evidence for multi-hop financial QA. We also release a curated subset of the benchmark (555 QA Pairs) to catalyze further research.

Existing regulatory frameworks for biomedical AI include robustness as a key component but lack detailed implementational guidance. The recent rise of biomedical foundation models creates new hurdles in testing and certification given their broad capabilities and susceptibility to complex distribution shifts. To balance test feasibility and effectiveness, we suggest a priority-based, task-oriented approach to tailor robustness evaluation objectives to a predefined specification. We urge concrete policies to adopt a granular categorization of robustness concepts in the specification. Our approach promotes the standardization of risk assessment and monitoring, which guides technical developments and mitigation efforts.

Quantifying the similarity between a group of companies has proven to be useful for several purposes, including company benchmarking, fraud detection, and searching for investment opportunities. This exercise can be done using a variety of data sources, such as company activity data and financial data. However, ledger account data is widely available and is standardized to a large extent. Such ledger accounts within a financial statement can be represented by means of a tree, i.e. a special type of graph, representing both the values of the ledger accounts and the relationships between them. Given their broad availability and rich information content, financial statements form a prime data source based on which company similarities or distances could be computed. In this paper, we present a graph distance metric that enables one to compute the similarity between the financial statements of two companies. We conduct a comprehensive experimental study using real-world financial data to demonstrate the usefulness of our proposed distance metric. The experimental results show promising results on a number of use cases. This method may be useful for investors looking for investment opportunities, government officials attempting to identify fraudulent companies, and accountants looking to benchmark a group of companies based on their financial statements.

We introduce TeMLM, a set of transparency-first release artifacts for clinical language models. TeMLM unifies provenance, data transparency, modeling transparency, and governance into a single, machine-checkable release bundle. We define an artifact suite (TeMLM-Card, TeMLM-Datasheet, TeMLM-Provenance) and a lightweight conformance checklist for repeatable auditing. We instantiate the artifacts on Technetium-I, a large-scale synthetic clinical NLP dataset with 498,000 notes, 7.74M PHI entity annotations across 10 types, and ICD-9-CM diagnosis labels, and report reference results for ProtactiniumBERT (about 100 million parameters) on PHI de-identification (token classification) and top-50 ICD-9 code extraction (multi-label classification). We emphasize that synthetic benchmarks are valuable for tooling and process validation, but models should be validated on real clinical data prior to deployment.

A common strategy for fact-checking long-form content generated by Large Language Models (LLMs) is extracting simple claims that can be verified independently. Since inaccurate or incomplete claims compromise fact-checking results, ensuring claim quality is critical. However, the lack of a standardized evaluation framework impedes assessment and comparison of claim extraction methods. To address this gap, we propose a framework for evaluating claim extraction in the context of fact-checking along with automated, scalable, and replicable methods for applying this framework, including novel approaches for measuring coverage and decontextualization. We also introduce Claimify, an LLM-based claim extraction method, and demonstrate that it outperforms existing methods under our evaluation framework. A key feature of Claimify is its ability to handle ambiguity and extract claims only when there is high confidence in the correct interpretation of the source text.

We present a generic framework for creating differentially private versions of any hypothesis test in a black-box way. We analyze the resulting tests analytically and experimentally. Most crucially, we show good practical performance for small data sets, showing that at epsilon = 1 we only need 5-6 times as much data as in the fully public setting. We compare our work to the one existing framework of this type, as well as to several individually-designed private hypothesis tests. Our framework is higher power than other generic solutions and at least competitive with (and often better than) individually-designed tests.

Recent LLMs have demonstrated promising ability in solving finance related problems. However, applying LLMs in real-world finance application remains challenging due to its high risk and high stakes property. This paper introduces FinTrust, a comprehensive benchmark specifically designed for evaluating the trustworthiness of LLMs in finance applications. Our benchmark focuses on a wide range of alignment issues based on practical context and features fine-grained tasks for each dimension of trustworthiness evaluation. We assess eleven LLMs on FinTrust and find that proprietary models like o4-mini outperforms in most tasks such as safety while open-source models like DeepSeek-V3 have advantage in specific areas like industry-level fairness. For challenging task like fiduciary alignment and disclosure, all LLMs fall short, showing a significant gap in legal awareness. We believe that FinTrust can be a valuable benchmark for LLMs' trustworthiness evaluation in finance domain.

Federated learning (FL) is the most practical multi-source learning method for electronic healthcare records (EHR). Despite its guarantee of privacy protection, the wide application of FL is restricted by two large challenges: the heterogeneous EHR systems, and the non-i.i.d. data characteristic. A recent research proposed a framework that unifies heterogeneous EHRs, named UniHPF. We attempt to address both the challenges simultaneously by combining UniHPF and FL. Our study is the first approach to unify heterogeneous EHRs into a single FL framework. This combination provides an average of 3.4% performance gain compared to local learning. We believe that our framework is practically applicable in the real-world FL.

Since the launch of ChatGPT, a powerful AI Chatbot developed by OpenAI, large language models (LLMs) have made significant advancements in both academia and industry, bringing about a fundamental engineering paradigm shift in many areas. While LLMs are powerful, it is also crucial to best use their power where "prompt'' plays a core role. However, the booming LLMs themselves, including excellent APIs like ChatGPT, have several inherent limitations: 1) temporal lag of training data, and 2) the lack of physical capabilities to perform external actions. Recently, we have observed the trend of utilizing prompt-based tools to better utilize the power of LLMs for downstream tasks, but a lack of systematic literature and standardized terminology, partly due to the rapid evolution of this field. Therefore, in this work, we survey related prompting tools and promote the concept of the "Prompting Framework" (PF), i.e. the framework for managing, simplifying, and facilitating interaction with large language models. We define the lifecycle of the PF as a hierarchical structure, from bottom to top, namely: Data Level, Base Level, Execute Level, and Service Level. We also systematically depict the overall landscape of the emerging PF field and discuss potential future research and challenges. To continuously track the developments in this area, we maintain a repository at https://github.com/lxx0628/Prompting-Framework-Survey, which can be a useful resource sharing platform for both academic and industry in this field.

The ModelWriter platform provides a generic framework for automated traceability analysis. In this paper, we demonstrate how this framework can be used to trace the consistency and completeness of technical documents that consist of a set of System Installation Design Principles used by Airbus to ensure the correctness of aircraft system installation. We show in particular, how the platform allows the integration of two types of reasoning: reasoning about the meaning of text using semantic parsing and description logic theorem proving; and reasoning about document structure using first-order relational logic and finite model finding for traceability analysis.

The emergence of large language models (LLMs) has significantly influenced numerous fields, including healthcare, by enhancing the capabilities of automated systems to process and generate human-like text. However, despite their advancements, the reliability and accuracy of LLMs in medical contexts remain critical concerns. Current evaluation methods often lack robustness and fail to provide a comprehensive assessment of LLM performance, leading to potential risks in clinical settings. In this work, we propose Med-CoDE, a specifically designed evaluation framework for medical LLMs to address these challenges. The framework leverages a critique-based approach to quantitatively measure the degree of disagreement between model-generated responses and established medical ground truths. This framework captures both accuracy and reliability in medical settings. The proposed evaluation framework aims to fill the existing gap in LLM assessment by offering a systematic method to evaluate the quality and trustworthiness of medical LLMs. Through extensive experiments and case studies, we illustrate the practicality of our framework in providing a comprehensive and reliable evaluation of medical LLMs.

Can foundation models be guided to execute tasks involving legal reasoning? We believe that building a benchmark to answer this question will require sustained collaborative efforts between the computer science and legal communities. To that end, this short paper serves three purposes. First, we describe how IRAC-a framework legal scholars use to distinguish different types of legal reasoning-can guide the construction of a Foundation Model oriented benchmark. Second, we present a seed set of 44 tasks built according to this framework. We discuss initial findings, and highlight directions for new tasks. Finally-inspired by the Open Science movement-we make a call for the legal and computer science communities to join our efforts by contributing new tasks. This work is ongoing, and our progress can be tracked here: https://github.com/HazyResearch/legalbench.

The Russian Financial Statements Database (RFSD) is an open, harmonized collection of annual unconsolidated financial statements of the universe of Russian firms in 2011-2023. It is the first open data set with information on every active firm in the country, including non-filing firms. With 56.6 million geolocated firm-year observations gathered from two official sources, the RFSD features multiple end-user quality-of-life improvements such as data imputation, statement articulation, harmonization across data providers and formats, and data enrichment. Extensive internal and external validation shows that most statements articulate well while their aggregates display higher correlation with the regional GDP than the previous gridded GDP data products. We also examine the direction and magnitude of the reporting bias by comparing the universe of firms that are required to file with the actual filers. The RFSD can be used in various economic applications as diverse as calibration of micro-founded models, estimation of markups and productivity, or assessing industry organization and market power.

This position paper argues that AI-assisted software engineering requires explicit mechanisms for tracking the epistemic status and temporal validity of architectural decisions. LLM coding assistants generate decisions faster than teams can validate them, yet no widely-adopted framework distinguishes conjecture from verified knowledge, prevents trust inflation through conservative aggregation, or detects when evidence expires. We propose three requirements for responsible AI-assisted engineering: (1) epistemic layers that separate unverified hypotheses from empirically validated claims, (2) conservative assurance aggregation grounded in the Gödel t-norm that prevents weak evidence from inflating confidence, and (3) automated evidence decay tracking that surfaces stale assumptions before they cause failures. We formalize these requirements as the First Principles Framework (FPF), ground its aggregation semantics in fuzzy logic, and define a quintet of invariants that any valid aggregation operator must satisfy. Our retrospective audit applying FPF criteria to two internal projects found that 20-25% of architectural decisions had stale evidence within two months, validating the need for temporal accountability. We outline research directions including learnable aggregation operators, federated evidence sharing, and SMT-based claim validation.

Large Language Models (LLMs) exhibit considerable promise in financial applications; however, prevailing models frequently demonstrate limitations when confronted with scenarios that necessitate sophisticated reasoning capabilities, stringent trustworthiness criteria, and efficient adaptation to domain-specific requirements. We introduce the Agentar-Fin-R1 series of financial large language models (8B and 32B parameters), specifically engineered based on the Qwen3 foundation model to enhance reasoning capabilities, reliability, and domain specialization for financial applications. Our optimization approach integrates a high-quality, systematic financial task label system with a comprehensive multi-layered trustworthiness assurance framework. This framework encompasses high-quality trustworthy knowledge engineering, multi-agent trustworthy data synthesis, and rigorous data validation governance. Through label-guided automated difficulty-aware optimization, tow-stage training pipeline, and dynamic attribution systems, we achieve substantial improvements in training efficiency. Our models undergo comprehensive evaluation on mainstream financial benchmarks including Fineva, FinEval, and FinanceIQ, as well as general reasoning datasets such as MATH-500 and GPQA-diamond. To thoroughly assess real-world deployment capabilities, we innovatively propose the Finova evaluation benchmark, which focuses on agent-level financial reasoning and compliance verification. Experimental results demonstrate that Agentar-Fin-R1 not only achieves state-of-the-art performance on financial tasks but also exhibits exceptional general reasoning capabilities, validating its effectiveness as a trustworthy solution for high-stakes financial applications. The Finova bench is available at https://github.com/antgroup/Finova.

Recent breakthroughs in zero-shot voice synthesis have enabled imitating a speaker's voice using just a few seconds of recording while maintaining a high level of realism. Alongside its potential benefits, this powerful technology introduces notable risks, including voice fraud and speaker impersonation. Unlike the conventional approach of solely relying on passive methods for detecting synthetic data, watermarking presents a proactive and robust defence mechanism against these looming risks. This paper introduces an innovative audio watermarking framework that encodes up to 32 bits of watermark within a mere 1-second audio snippet. The watermark is imperceptible to human senses and exhibits strong resilience against various attacks. It can serve as an effective identifier for synthesized voices and holds potential for broader applications in audio copyright protection. Moreover, this framework boasts high flexibility, allowing for the combination of multiple watermark segments to achieve heightened robustness and expanded capacity. Utilizing 10 to 20-second audio as the host, our approach demonstrates an average Bit Error Rate (BER) of 0.48\% across ten common attacks, a remarkable reduction of over 2800\% in BER compared to the state-of-the-art watermarking tool. See https://aka.ms/wavmark for demos of our work.

Government fiscal policies, particularly annual union budgets, exert significant influence on financial markets. However, real-time analysis of budgetary impacts on sector-specific equity performance remains methodologically challenging and largely unexplored. This study proposes a framework to systematically identify and rank sectors poised to benefit from India's Union Budget announcements. The framework addresses two core tasks: (1) multi-label classification of excerpts from budget transcripts into 81 predefined economic sectors, and (2) performance ranking of these sectors. Leveraging a comprehensive corpus of Indian Union Budget transcripts from 1947 to 2025, we introduce BASIR (Budget-Assisted Sectoral Impact Ranking), an annotated dataset mapping excerpts from budgetary transcripts to sectoral impacts. Our architecture incorporates fine-tuned embeddings for sector identification, coupled with language models that rank sectors based on their predicted performances. Our results demonstrate 0.605 F1-score in sector classification, and 0.997 NDCG score in predicting ranks of sectors based on post-budget performances. The methodology enables investors and policymakers to quantify fiscal policy impacts through structured, data-driven insights, addressing critical gaps in manual analysis. The annotated dataset has been released under CC-BY-NC-SA-4.0 license to advance computational economics research.

The race to train language models on vast, diverse, and inconsistently documented datasets has raised pressing concerns about the legal and ethical risks for practitioners. To remedy these practices threatening data transparency and understanding, we convene a multi-disciplinary effort between legal and machine learning experts to systematically audit and trace 1800+ text datasets. We develop tools and standards to trace the lineage of these datasets, from their source, creators, series of license conditions, properties, and subsequent use. Our landscape analysis highlights the sharp divides in composition and focus of commercially open vs closed datasets, with closed datasets monopolizing important categories: lower resource languages, more creative tasks, richer topic variety, newer and more synthetic training data. This points to a deepening divide in the types of data that are made available under different license conditions, and heightened implications for jurisdictional legal interpretations of copyright and fair use. We also observe frequent miscategorization of licenses on widely used dataset hosting sites, with license omission of 72%+ and error rates of 50%+. This points to a crisis in misattribution and informed use of the most popular datasets driving many recent breakthroughs. As a contribution to ongoing improvements in dataset transparency and responsible use, we release our entire audit, with an interactive UI, the Data Provenance Explorer, which allows practitioners to trace and filter on data provenance for the most popular open source finetuning data collections: www.dataprovenance.org.

To reduce development overhead and enable seamless integration between potential components comprising any given generative AI application, the Model Context Protocol (MCP) (Anthropic, 2024) has recently been released and subsequently widely adopted. The MCP is an open protocol that standardizes API calls to large language models (LLMs), data sources, and agentic tools. By connecting multiple MCP servers, each defined with a set of tools, resources, and prompts, users are able to define automated workflows fully driven by LLMs. However, we show that the current MCP design carries a wide range of security risks for end users. In particular, we demonstrate that industry-leading LLMs may be coerced into using MCP tools to compromise an AI developer's system through various attacks, such as malicious code execution, remote access control, and credential theft. To proactively mitigate these and related attacks, we introduce a safety auditing tool, MCPSafetyScanner, the first agentic tool to assess the security of an arbitrary MCP server. MCPScanner uses several agents to (a) automatically determine adversarial samples given an MCP server's tools and resources; (b) search for related vulnerabilities and remediations based on those samples; and (c) generate a security report detailing all findings. Our work highlights serious security issues with general-purpose agentic workflows while also providing a proactive tool to audit MCP server safety and address detected vulnerabilities before deployment. The described MCP server auditing tool, MCPSafetyScanner, is freely available at: https://github.com/johnhalloran321/mcpSafetyScanner

LLM test-time compute (or LLM inference) via search has emerged as a promising research area with rapid developments. However, current frameworks often adopt distinct perspectives on three key aspects (task definition, LLM profiling, and search procedures), making direct comparisons challenging. Moreover, the search algorithms employed often diverge from standard implementations, and their specific characteristics are not thoroughly specified. In this survey, we provide a comprehensive technical review that unifies task definitions and provides modular definitions of LLM profiling and search procedures. The definitions enable precise comparisons of various LLM inference frameworks while highlighting their departures from conventional search algorithms. We also discuss the applicability, performance, and efficiency of these methods. For further details and ongoing updates, please refer to our GitHub repository: https://github.com/xinzhel/LLM-Agent-Survey/blob/main/search.md

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial for complex tasks, present challenges in scalability, reliability, and potential misuse. Decentralized systems offer a solution by distributing workload and mitigating central points of failure, but they introduce risks of unauthorized access to sensitive data across nodes. We address these challenges with a comprehensive framework designed for responsible AI development. Our approach incorporates: 1) Zero-knowledge proofs for secure model verification, enhancing trust without compromising privacy. 2) Consensus-based verification checks to ensure consistent outputs across nodes, mitigating hallucinations and maintaining model integrity. 3) Split Learning techniques that segment models across different nodes, preserving data privacy by preventing full data access at any point. 4) Hardware-based security through trusted execution environments (TEEs) to protect data and computations. This framework aims to enhance security and privacy and improve the reliability and fairness of multimodal AI systems. Promoting efficient resource utilization contributes to more sustainable AI development. Our state-of-the-art proofs and principles demonstrate the framework's effectiveness in responsibly democratizing artificial intelligence, offering a promising approach for building secure and private foundational models.

Automating software vulnerability detection (SVD) remains a critical challenge in an era of increasingly complex and interdependent software systems. Despite significant advances in Large Language Models (LLMs) for code analysis, prevailing evaluation methodologies often lack the context-aware robustness necessary to capture real-world intricacies and cross-component interactions. To address these limitations, we present VulnSage, a comprehensive evaluation framework and a dataset curated from diverse, large-scale open-source system software projects developed in C/C++. Unlike prior datasets, it leverages a heuristic noise pre-filtering approach combined with LLM-based reasoning to ensure a representative and minimally noisy spectrum of vulnerabilities. The framework supports multi-granular analysis across function, file, and inter-function levels and employs four diverse zero-shot prompt strategies: Baseline, Chain-of-Thought, Think, and Think & Verify. Through this evaluation, we uncover that structured reasoning prompts substantially improve LLM performance, with Think & Verify reducing ambiguous responses from 20.3% to 9.1% while increasing accuracy. We further demonstrate that code-specialized models consistently outperform general-purpose alternatives, with performance varying significantly across vulnerability types, revealing that no single approach universally excels across all security contexts. Link to dataset and codes: https://github.com/Erroristotle/VulnSage.git

We consider an online learning problem with one-sided feedback, in which the learner is able to observe the true label only for positively predicted instances. On each round, k instances arrive and receive classification outcomes according to a randomized policy deployed by the learner, whose goal is to maximize accuracy while deploying individually fair policies. We first extend the framework of Bechavod et al. (2020), which relies on the existence of a human fairness auditor for detecting fairness violations, to instead incorporate feedback from dynamically-selected panels of multiple, possibly inconsistent, auditors. We then construct an efficient reduction from our problem of online learning with one-sided feedback and a panel reporting fairness violations to the contextual combinatorial semi-bandit problem (Cesa-Bianchi & Lugosi, 2009, Gy\"{o}rgy et al., 2007). Finally, we show how to leverage the guarantees of two algorithms in the contextual combinatorial semi-bandit setting: Exp2 (Bubeck et al., 2012) and the oracle-efficient Context-Semi-Bandit-FTPL (Syrgkanis et al., 2016), to provide multi-criteria no regret guarantees simultaneously for accuracy and fairness. Our results eliminate two potential sources of bias from prior work: the "hidden outcomes" that are not available to an algorithm operating in the full information setting, and human biases that might be present in any single human auditor, but can be mitigated by selecting a well chosen panel.

Clinical diagnosis is critical in medical practice, typically requiring a continuous and evolving process that includes primary diagnosis, differential diagnosis, and final diagnosis. However, most existing clinical diagnostic tasks are single-step processes, which does not align with the complex multi-step diagnostic procedures found in real-world clinical settings. In this paper, we propose a multi-step diagnostic task and annotate a clinical diagnostic dataset (MSDiagnosis). This dataset includes primary diagnosis, differential diagnosis, and final diagnosis questions. Additionally, we propose a novel and effective framework. This framework combines forward inference, backward inference, reflection, and refinement, enabling the LLM to self-evaluate and adjust its diagnostic results. To assess the effectiveness of our proposed method, we design and conduct extensive experiments. The experimental results demonstrate the effectiveness of the proposed method. We also provide a comprehensive experimental analysis and suggest future research directions for this task.

This paper proposes a formal framework for reverse stress testing geopolitical risk in corporate credit portfolios. A joint macro-financial scenario vector, augmented with an explicit geopolitical risk factor, is mapped into stressed probabilities of default and losses given default. These stresses are then propagated to portfolio tail losses through a latent factor structure and translated into a stressed CET1 ratio, jointly accounting for capital depletion and risk-weighted asset dynamics. Reverse stress testing is formulated as a constrained maximum likelihood problem over the scenario space. This yields a geopolitical point reverse stress test, or design point, defined as the most probable scenario that breaches a prescribed capital adequacy constraint under a reference distribution. The framework further characterises neighbourhoods and near optimal sets of reverse stress scenarios, allowing for sensitivity analysis and governance oriented interpretation. The approach is compatible with internal rating based models and supports implementation at the exposure or sector level.

We present LLM-KT, a flexible framework designed to enhance collaborative filtering (CF) models by seamlessly integrating LLM (Large Language Model)-generated features. Unlike existing methods that rely on passing LLM-generated features as direct inputs, our framework injects these features into an intermediate layer of any CF model, allowing the model to reconstruct and leverage the embeddings internally. This model-agnostic approach works with a wide range of CF models without requiring architectural changes, making it adaptable to various recommendation scenarios. Our framework is built for easy integration and modification, providing researchers and developers with a powerful tool for extending CF model capabilities through efficient knowledge transfer. We demonstrate its effectiveness through experiments on the MovieLens and Amazon datasets, where it consistently improves baseline CF models. Experimental studies showed that LLM-KT is competitive with the state-of-the-art methods in context-aware settings but can be applied to a broader range of CF models than current approaches.

EHR audit logs are a highly granular stream of events that capture clinician activities, and is a significant area of interest for research in characterizing clinician workflow on the electronic health record (EHR). Existing techniques to measure the complexity of workflow through EHR audit logs (audit logs) involve time- or frequency-based cross-sectional aggregations that are unable to capture the full complexity of a EHR session. We briefly evaluate the usage of transformer-based tabular language model (tabular LM) in measuring the entropy or disorderedness of action sequences within workflow and release the evaluated models publicly.

Standardized datasets and benchmarks have spurred innovations in computer vision, natural language processing, multi-modal and tabular settings. We note that, as compared to other well researched fields, fraud detection has unique challenges: high-class imbalance, diverse feature types, frequently changing fraud patterns, and adversarial nature of the problem. Due to these, the modeling approaches evaluated on datasets from other research fields may not work well for the fraud detection. In this paper, we introduce Fraud Dataset Benchmark (FDB), a compilation of publicly available datasets catered to fraud detection FDB comprises variety of fraud related tasks, ranging from identifying fraudulent card-not-present transactions, detecting bot attacks, classifying malicious URLs, estimating risk of loan default to content moderation. The Python based library for FDB provides a consistent API for data loading with standardized training and testing splits. We demonstrate several applications of FDB that are of broad interest for fraud detection, including feature engineering, comparison of supervised learning algorithms, label noise removal, class-imbalance treatment and semi-supervised learning. We hope that FDB provides a common playground for researchers and practitioners in the fraud detection domain to develop robust and customized machine learning techniques targeting various fraud use cases.

Central to long-form text generation in vertical domains is the "impossible trinity" confronting current large language models (LLMs): the simultaneous achievement of low hallucination, deep logical coherence, and personalized expression. This study establishes that this bottleneck arises from existing generative paradigms succumbing to the Statistical Smoothing Trap, a phenomenon that overlooks the high-entropy information acquisition and structured cognitive processes integral to expert-level writing. To address this limitation, we propose the DeepNews Framework, an agentic workflow that explicitly models the implicit cognitive processes of seasoned financial journalists. The framework integrates three core modules: first, a dual-granularity retrieval mechanism grounded in information foraging theory, which enforces a 10:1 saturated information input ratio to mitigate hallucinatory outputs; second, schema-guided strategic planning, a process leveraging domain expert knowledge bases (narrative schemas) and Atomic Blocks to forge a robust logical skeleton; third, adversarial constraint prompting, a technique deploying tactics including Rhythm Break and Logic Fog to disrupt the probabilistic smoothness inherent in model-generated text. Experiments delineate a salient Knowledge Cliff in deep financial reporting: content truthfulness collapses when retrieved context falls below 15,000 characters, while a high-redundancy input exceeding 30,000 characters stabilizes the Hallucination-Free Rate (HFR) above 85%. In an ecological validity blind test conducted with a top-tier Chinese technology media outlet, the DeepNews system--built on a previous-generation model (DeepSeek-V3-0324)-achieved a 25% submission acceptance rate, significantly outperforming the 0% acceptance rate of zero-shot generation by a state-of-the-art (SOTA) model (GPT-5).