← Search

Haoxiang Jia

2 accepted papers

2025

Alleviating Shifted Distribution in Human Preference Alignment through Meta-Learning

AAAI 2025technical

The capability of the reward model (RM) is crucial for the success of Reinforcement Learning from Human Feedback (RLHF) in aligning with human preferences. However, as training progresses, the output space distribution of the policy model shifts. The RM, initially trained on responses sampled from t…

Cited by 0SourcePDFScholar
2024

StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback

ACL 2024long

The advancement of large language models (LLMs) has significantly propelled the field of code generation. Previous work integrated reinforcement learning (RL) with compiler feedback for exploring the output space of LLMs to enhance code generation quality. However, the lengthy code generated by LLMs…