6 papers
Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models
Siyuan Zhang, Jialian Li, Yichi Zhang +3
Large Language Models have achieved remarkable performance on reasoning tasks, motivating research into how this ability evolves during training. Prior work has primarily analyzed…
Task Aware Dreamer for Task Generalization in Reinforcement Learning
Chengyang Ying, Xinning Zhou, Zhongkai Hao +4
A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with d…
3D-Properties: Identifying Challenges in DPO and Charting a Path Forward
Yuzi Yan, Yibo Miao, Jialian Li +4
Aligning large language models (LLMs) with human preferences has gained significant attention, with Proximal Policy Optimization (PPO) as a standard yet computationally expensive m…
Exploring the LLM Journey from Cognition to Expression with Linear Representations
Yuzi Yan, Jialian Li, Yipin Zhang +1
This paper presents an in-depth examination of the evolution and interplay of cognitive and expressive capabilities in large language models (LLMs), with a specific focus on Baichu…
Boosting Deductive Reasoning with Step Signals In RLHF
Jialian Li, Yipin Zhang, Wei Shen +3
Logical reasoning is a crucial task for Large Language Models (LLMs), enabling them to tackle complex problems. Among reasoning tasks, multi-step reasoning poses a particular chall…
Reward-Robust RLHF in LLMs
Yuzi Yan, Xingzhou Lou, Jialian Li +6
As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pat…