5 papers
Exploration-Preserving Policy Optimization
Hangzhan jin, Mohammad Hamdaqa, Doina Precup
Reinforcement learning with verifiable rewards improves reasoning, while the allocation of learning signal shapes which solutions remain accessible under repeated sampling. Group-r…
Rotation-Preserving Supervised Fine-Tuning
Hangzhan Jin, Tianwei Ni, Lu Li +3
Supervised fine-tuning (SFT) improves in-domain performance but can degrade out-of-domain (OOD) generalization. Prior work suggests that this degradation is related to changes in d…
RL Fine-Tuning Heals OOD Forgetting in SFT
Hangzhan Jin, Sitao Luan, Tianwei Ni +5
Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (LLM) reasoning, but why it works remain…
RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs
Hangzhan Jin, Sicheng Lv, Sifan Wu +1
Training large language models (LLMs) from scratch is increasingly impractical, making post-training methods such as supervised fine-tuning (SFT) and reinforcement-learning fine-tu…
CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models
Hangzhan Jin, Mohammad Hamdaqa
Unlike code generation, which involves creating code from scratch, code completion focuses on integrating new lines or blocks of code into an existing codebase. This process requir…