4 papers
Understanding and Mitigating Premature Confidence for Better LLM Reasoning
Jingchu Gai, Guanning Zeng, Christina Baek +4
Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving rea…
Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards
Guanning Zeng, Zhaoyi Zhou, Daman Arora +1
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for post-training large reasoning models (LRMs) using policy-gradient methods such as GRPO.…
Maximum Likelihood Reinforcement Learning
Fahim Tajwar, Guanning Zeng, Yueer Zhou +7
Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling from the model. Our key observation…
Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
Jingchu Gai, Guanning Zeng, Huaqing Zhang +1
It is widely recognized that reinforcement learning (RL) fine-tuning of large language models often leads to diversity collapse, where outputs lack variety. Prior work has proposed…