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
arXiv:2609.34519v2 Announce Type: replace
Abstract: On-Policy Self-Distillation (OPSD) has emerged as a promising paradigm for safety alignment, delivering dense, token-level supervision by distillin...
By Qirui Liu, Yichen Sun, Yan Wang, Yu Mi, Wei Cao, Yue Shen, Zhixuan Chu, Kui Ren
arXiv:2606. 02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax.
By Hao Li, Jingkun An, Zijun Song, Pengyu Zhu, Rui Li, Hao Wang, Wendi Feng, Yesheng Liu, Lijun Li, Jin-Ge Yao, Lei Sha
arXiv:2605.10194v2 Announce Type: replace
Abstract: On-policy self-distillation (OPSD) uses a model as its own teacher under privileged context, providing token-level supervision on the model's own r...
By Jiaxuan Wang, Xuan Ouyang, Zhiyu Chen, Yulan Hu, Lan-Zhe Guo
EOPSA (Efficient On-Policy Self-Distilled Safety Alignment) addresses inefficiencies in On-Policy Self-Distillation (OPSD) for safety alignment by focusing training on safety-critical tokens. It introduces Adaptive Rollout Scheduling, which limits generation length based on a Teacher Rescue Rate metric, and Selective Distillation, which filters out safety-neutral tokens to concentrate gradient updates on safety-pivotal transitions. Experiments on models up to 32B parameters show that EOPSA reduces rollout computation by about 50% and backpropagates through only roughly 2% of tokens, outperforming full-token distillation baselines in safety compliance and reasoning retention.
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.
By ShengYun Peng, Pin-Yu Chen, Eric Smith, Song Jiang, Hongyuan Zhan, Haozhu Wang, Mahesh Pasupuleti, Duen Horng Chau, Jianfeng Chi
arXiv:2608. 03745v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring.
By Dominik Meier, Luca Joshua Francis, Marco Bernhard Kaiser, Terry Ruas, Jan Philip Wahle, Bela Gipp
arXiv:2604.23238v3 Announce Type: replace-cross
Abstract: Distillation via reasoning traces exposes frontier models to adversarial third parties, who can bypass their guardrails and misappropriate th...
By Max Hartman, Vidhata Jayaraman, Moulik Choraria, Lav R. Varshney
arXiv:2605.28791v2 Announce Type: replace-cross
Abstract: On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes in...
By Jiazhen Huang, Xiao Chen, Xiao Luo, Yong Dai, Senkang Hu, Yuzhi Zhao
arXiv:2602. 17686v5 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) reasoning has significantly improved LLMs' mathematical problem-solving capabilities, but distilling such capabilities into smaller models remains challenging due to the capacity mismatch between verbose teachers and compact students.
By Bowen Yu, Sheng Zhang, Binhao Wang, Yi Wen, Jingtong Gao, Bowen Liu, Zimo Zhao, Shanshan Ye, Wanyu Wang, Maolin Wang, Xiangyu Zhao
arXiv:2602. 22495v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students.
By Zhaoyang Zhang, Shuli Jiang, Yantao Shen, Yuting Zhang, Dhananjay Ram, Shuo Yang, Zhuowen Tu, Wei Xia, Stefano Soatto
arXiv:2610.27555v1 Announce Type: cross
Abstract: Safety pretraining has emerged as a promising paradigm for embedding safety deeply into a model during pretraining, yielding robustness to subsequent...
By Bingqi Shang, Yang Zhang, Yiwei Chen, Changsheng Wang, Shiyu Chang, Bingquan Shen, Sijia Liu