3 papers
cs.LG2026
Policy Improvement Reinforcement Learning
Huaiyang Wang, Xiaojie Li, Xiaohan Wang +10
Reinforcement learning has become a central post-training paradigm for improving LLM and agent capabilities. Yet existing RL post-training methods share a common blind spot: they c…
cs.AI2025
Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment
Lijun Zhang, Lin Li, Wei Wei +5
When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existi…
cs.LG2025
Risk-aware Direct Preference Optimization under Nested Risk Measure
Lijun Zhang, Lin Li, Yajie Qi +4
When fine-tuning pre-trained Large Language Models (LLMs) to align with human values and intentions, maximizing the estimated reward can lead to superior performance, but it also i…