4 papers · 1 filter
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Qiying Yu, Zheng Zhang, Ruofei Zhu +32
Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details…
A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimization
Wenyuan Xu, Xiaochen Zuo, Chao Xin +3
Reinforcement Learning from Human Feedback (RLHF) has emerged as a important paradigm for aligning large language models (LLMs) with human preferences during post-training. This fr…
Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback
Wei Shen, Guanlin Liu, Zheng Wu +5
Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning large language models with human preferences. While recent research has focused on algorithmic improvement…
What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret
Yufeng Yuan, Yu Yue, Ruofei Zhu +2
Reinforcement learning (RL) is pivotal for enabling large language models (LLMs) to generate long chains of thought (CoT) for complex tasks like math and reasoning. However, Proxim…