paper-with-me

홈 › Papers

Teaching Language Models to Critique via Reinforcement Learning

2025-02-05 · Zhihui Xie, Jie Chen, Liyu Chen, Weichao Mao, Jingjing Xu, Lingpeng Kong

Teaching large language models (LLMs) to critique and refine their outputs is crucial for building systems that can iteratively improve, yet it is fundamentally limited by the ability to provide accurate judgments and actionable suggestions. In this work, we study LLM critics for code generation and propose $\texttt{CTRL}$, a framework for $\texttt{C}$ritic $\texttt{T}$raining via $\texttt{R}$einforcement $\texttt{L}$earning, which trains a critic model to generate feedback that maximizes correction performance for a fixed generator model without human supervision. Our results demonstrate that critics trained with $\texttt{CTRL}$ significantly enhance pass rates and mitigate compounding errors across both base and stronger generator models. Furthermore, we show that these critic models act as accurate generative reward models and enable test-time scaling through iterative critique-revision, achieving up to 106.1% relative improvements across challenging code generation benchmarks.

📄 PDF Abstract BibTeX arXiv:2502.03492

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generationreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning

2025-09-26 · Chi Ruan, Dongfu Jiang, Yubo Wang, Wenhu Chen arxiv

Reinforcement Learning (RL) has emerged as a popular training paradigm, particularly when paired with reasoning models. While effective, it primarily focuses on generating responses and lacks mechanisms to explicitly fos…

Reinforcement LearningCode Generation

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

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

2026-04-13 · Haozhe Wang, Cong Wei, Weiming Ren, Jiaming Liu 외 arxiv

Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimen…

Reinforcement Learning

Self-Generated Critiques Boost Reward Modeling for Language Models

2024-11-25 · Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan 외

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 an…

RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs

2023-05-15 · Afra Feyza Akyürek, Ekin Akyürek, Aman Madaan, Ashwin Kalyan 외

Despite their unprecedented success, even the largest language models make mistakes. Similar to how humans learn and improve using feedback, previous work proposed providing language models with natural language feedback…

reinforcement-learningRetrievaltext similarity