4 papers
Entropy-Regularized Process Reward Model
Hanning Zhang, Pengcheng Wang, Shizhe Diao +6
Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic error…
On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
Yong Lin, Skyler Seto, Maartje ter Hoeve +6
Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences. Central to RLHF is learning a reward function for scor…
Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
Yifei He, Yuzheng Hu, Yong Lin +2
Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each. Existing…
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Rui Yang, Ruomeng Ding, Yong Lin +2
Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning f…