paper-with-me

Papers

Self-Generated Critiques Boost Reward Modeling for Language Models

2024-11-25 · Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to incorporate critiques in a natural language format. We hypothesize that predicting both critiques and the scalar reward would improve reward modeling ability. Motivated by this, we propose Critic-RM, a framework that improves reward models using self-generated critiques without extra supervision. Critic-RM employs a two-stage process: generating and filtering high-quality critiques, followed by joint fine-tuning on reward prediction and critique generation. Experiments across benchmarks show that Critic-RM improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges, demonstrating strong performance and data efficiency. Additional studies further validate the effectiveness of generated critiques in rectifying flawed reasoning steps with 2.5%-3.2% gains in improving reasoning accuracy.

📄 PDF Abstract BibTeX arXiv:2411.16646

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Reward Modeling from Natural Language Human Feedback

2026-01-12 · Zongqi Wang, Rui Wang, Yuchuan Wu, Yiyao Yu 외 arxiv

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chai…

Reinforcement LearningBinary Classification

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique

2025-03-21 · Yansi Li, Jiahao Xu, Tian Liang, Xingyu Chen 외

Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Traditional inference time scaling methods ut…

Decision Making

Small Language Models Need Strong Verifiers to Self-Correct Reasoning

2024-04-26 · Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim 외

Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated critiques that pinpoint the errors. This work…

Math

Teaching Large Reasoning Models Effective Reflection

2026-01-19 · Hanbin Wang, Jingwei Song, Jinpeng Li, Qi Zhu 외 arxiv

Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks, often by engaging in self-reflective behaviors such as self-critique and backtracking. However, not all reflections are…

Reinforcement Learning

Improving Reward Models with Synthetic Critiques

2024-05-31 · Zihuiwen Ye, Fraser Greenlee-Scott, Max Bartolo, Phil Blunsom 외

Reward models (RMs) play a critical role in aligning language models through the process of reinforcement learning from human feedback. RMs are trained to predict a score reflecting human preference, which requires signi…

Instruction Following