6 papers · 1 filter
Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
Sagnik Mukherjee, Lifan Yuan, Pavan Jayasinha +2
Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling e…
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
Sagnik Mukherjee, Lifan Yuan, Dilek Hakkani-Tur +1
Reinforcement learning (RL) yields substantial improvements in large language models (LLMs) downstream task performance and alignment with human values. Surprisingly, such large ga…
Process Reinforcement through Implicit Rewards
Ganqu Cui, Lifan Yuan, Zefan Wang +22
Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in ta…
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
Ganqu Cui, Yuchen Zhang, Jiacheng Chen +14
This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy. Such phenomenon is consistently observed across vast RL r…
The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
Shivam Agarwal, Zimin Zhang, Lifan Yuan +2
Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled da…
Free Process Rewards without Process Labels
Lifan Yuan, Wendi Li, Huayu Chen +6
Different from its counterpart outcome reward models (ORMs), which evaluate the entire responses, a process reward model (PRM) scores a reasoning trajectory step by step, providing…