Weight Ensembling Improves Reasoning in Language Models

N/A

Published as a conference paper at COLM 2025 Weight Ensembling Improves Reasoning in Language Models Xingyu Dang⋆,1 Christina Baek⋆,2 Kaiyue Wen3 Zico Kolter2 Aditi Raghunathan2 1 Tsinghua University 2 Carnegie Mellon University 3 Stanford University # dangxy20@mails.tsinghua.edu.cn, kbaek@andrew.cmu.edu…

related reading

• [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• Self-Adapting Language Modelsarxiv.org
• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• [2506.19733] Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?arxiv.org
• Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Modelsarxiv.org
• 2401.10020.pdfarxiv.org
• [2509.14786] Pre-training under infinite computearxiv.org
• Mode-Conditioning Unlocks Superior Test-Time Scalingarxiv.org
• Language Model Compositionarxiv.org
• [2605.12715] Scaling Laws for Mixture Pretraining Under Data Constraintsarxiv.org
• Position: It's Time to Optimize for Self-Consistencytime-for-consistency.github.io