← Back to all news
arXiv Machine Learning By ShengYun Peng, Pin-Yu Chen, Eric Smith, Song Jiang, Hongyuan Zhan, Haozhu Wang, Mahesh Pasupuleti, Duen Horng Chau, Jianfeng Chi

Large Reasoning Models Learn Better Alignment from Flawed Thinking

Read the original on arXiv Machine Learning →

Large reasoning models generate chain-of-thought (CoT) before answering but struggle with safety alignment and can be misled by flawed premises. The paper introduces RECAP, a reinforcement learning approach that trains models to override flawed reasoning paths and produce safe, helpful responses without extra training cost. RECAP improves safety, jailbreak robustness, and reduces overrefusal while preserving core reasoning abilities and inference token budget.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jul 7

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models

arXiv:2607. 02914v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness, and trustworthiness remains a persistent challenge.

By Jiyang Guan, Yong Xie, Jun Chen, Jiexi Liu, Zipeng Ye, Defeng Li, Jiayu Shen, Jialing Tao, Hui Xue
llmsreinforcement-learningfine-tuningbenchmarkssafety
More like this →
arXiv Machine Learning
Jun 2

Enhancing LLM Metacognition via Cognitive Pairwise Training

arXiv:2606. 00869v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its outcome-level rewards can make models more willing to give confident answers when evidence or reasoning is unreliable.

By Weitao Li, Hao Zhou, Xuanyu Lei, Fandong Meng, Yuanhang Liu, Jingyi Ren, Ante Wang, Xiaolong Wang, Yuanchi Zhang, Fuwen Luo, Guangwen Yang, Lin Gan, Weizhi Ma, Yang Liu
llmsreinforcement-learningfine-tuningsafety
More like this →
arXiv AI
Oct 19

Rethinking GRPO for Large Reasoning Model Safety Alignment

The paper "Rethinking GRPO for Large Reasoning Model Safety Alignment" identifies two failure modes in Group Relative Policy Optimization—advantage collapse and unsafe diversification—that weaken safety learning in large reasoning models. It proposes the Beacon framework, which includes Safety Signal Recovery (SSR) and Safety-Utility Decoupled Alignment (SUDA), to restore effective safety signals and mitigate over-refusal. Experiments on Qwen3 and DeepSeek-R1-Distill models across eight benchmarks demonstrate that Beacon improves safety performance by up to 32.83 percentage points while keeping over-refusal low.

By Jiawei Chen, Yi Zhang, Jiawei Du, Zhonghou Lv, Tairan Chen, Junyuan Shang, Jinchang Hou, Xiao Yang, Yu Tian, Chenfu Bao, Chao Yu, Zhaoxia Yin
benchmarkssafety
More like this →