This collection includes models from the paper "Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality".
Junliang Li
JunliangLi
AI & ML interests
LLM, RL, Graph Machine Learning
Recent Activity
authored
a paper
4 days ago
ERNIE 5.0 Technical Report
upvoted
a
paper
8 days ago
ERNIE 5.0 Technical Report
liked
a dataset
3 months ago
SimulaMet/Kvasir-VQA-x1
Organizations
