arXiv AI September 17, 2026 By Youjia Wang, Lin Xu, Yang Sun, Yuxiao Lu, Chengfang Fang, Jie Shi

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.

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 AI.

Hugging Face Trending Papers

Jun 4

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.

llms reinforcement-learning safety

arXiv AI

Sep 7

Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

The paper investigates how large language models balance helpfulness and safety by refusing harmful queries while responding to benign ones. It decomposes safety-tuning responses into a boilerplate refusal statement and a rationale, finding that the statement causes false refusals by relying on superficial cues. Training on rationales alone reduces false refusals without compromising safety performance, suggesting that fine‑grained safety supervision is essential for better alignment.

By Minji Kim, Hyounghun Kim

llms agents safety

arXiv AI

Sep 30

Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models

arXiv:2609.36254v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) are commonly trained with reinforcement learning (RL) to improve their generation of chain-of-thought (CoT) reasoning bef...

By Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan, Alexander Kotov, Dongxiao Zhu

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 6

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.

By Long P. Hoang, Hai V. Le, Shaoyang Xu, Wei Lu, Wenxuan Zhang

llms reinforcement-learning safety

arXiv AI

Jun 18

Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection

arXiv:2606. 19168v1 Announce Type: new Abstract: To achieve deeper safety alignment for large language models (LLMs), recent efforts have studied how to push safety interventions earlier into the pretraining stage, primarily by filtering unsafe data or rewriting it into safer forms.

By Jinhan Li, Kexian Tang, Yihan Xu, Zhuorui Ye, Kaifeng Lyu

llms fine-tuning safety

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

llms reinforcement-learning fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection

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