arXiv AI

Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models

The paper introduces SaLT-DPO, a Segment‑aware Listwise Target DPO method designed to improve safety in Large Reasoning Models (LRMs). It decomposes responses into reasoning and answer segments, scores each segment’s safety, and aligns length‑normalized rewards with soft target distributions over multiple candidates. The approach also incorporates joint safety coherence regularization and utility anchoring to reduce unsafe content while maintaining compliance and reasoning performance.

arXiv AI
Aug 26

TRACE: An Evidence-Grounded Benchmark for Safety Evaluation of Large Reasoning Models

TRACE is a new benchmark that evaluates the safety of Large Reasoning Models (LRMs) across the entire inference pipeline, including prompts, reasoning traces, and final responses. It provides prompts in two languages covering nine risk categories and ten attack strategies, and for each prompt four LRMs generate traces and responses that are annotated for safety with supporting evidence extracted from the source text. Evaluation of 18 guardrail models on TRACE shows that detecting unsafe content in reasoning traces is much harder than in prompts or final responses, and that current models struggle to extract the necessary evidence.

By Zhenyu Wu, Siyuan Chen, Changchun Yang, Jiaqi Dong, Min Zhou, Ali Almadan, Talal Hammad, Faisal Wahbo, Aminullah Tora, Mona Alshahrani, Xin Gao
arXiv AI
Sep 17

First Token Matters: Understanding Safety Collapse in Large Reasoning Models

The paper investigates why large reasoning models (LRMs) lose safety alignment when faced with harmful queries. By analyzing token-level refusal dynamics, the authors identify a vulnerability called Onset Refusal Collapse (ORC), where the refusal signal drops sharply at the first generated token, leading to unsafe responses. They introduce SafeToken, a lightweight inference-time intervention that injects a learned safety anchor at reasoning onset, which mitigates ORC, improves safety on harmful-query benchmarks, and largely preserves reasoning utility.

By Yizheng Yang, Haining Yu, Yuechen Wang, Yikai Hou, Xing Fu, Jinbo Yang, Tianqing Zhu
arXiv AI
Sep 17

Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models

The paper introduces "cunning questions"—non‑safety prompts that contain misleading premises or subtle inconsistencies—to train large language models (LLMs) to scrutinize underlying intent and assumptions. Experiments show that incorporating these questions improves robustness against out‑of‑distribution jailbreak attacks and enhances subsequent safety fine‑tuning, achieving a new state‑of‑the‑art reduction in mean ASR from 17.40% to 15.05% across nine backbone–benchmark combinations. The authors argue that this training fosters vigilance, enabling models to prioritize safety judgments before engaging in harmful planning.

By Youjia Wang, Lin Xu, Yang Sun, Yuxiao Lu, Chengfang Fang, Jie Shi
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
arXiv Machine Learning
Aug 31

Large Reasoning Models Learn Better Alignment from Flawed Thinking

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