arXiv AI September 7, 2026 By Minji Kim, Hyounghun Kim

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.

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

Sep 1

Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges

Safety benchmarks for large language models often assess the risk of a user query, although the outcome of question answering depends on whether the response violates a policy. This distinction is cri...

llms nlp benchmarks safety

arXiv AI

Jun 30

CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models

arXiv:2501. 14940v4 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption.

By Guangzhi Sun, Xiao Zhan, Shutong Feng, Philip C. Woodland, Jose Such

llms benchmarks safety

arXiv AI

Sep 2

Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges

arXiv:2609.01210v1 Announce Type: cross Abstract: Safety benchmarks for large language models often assess the risk of a user query, although the outcome of question answering depends on whether the...

By Rui Yang, Shuang Huang, Junhua Liu, Ziqi Zhao, Qingzhong Yan, Yuhang Sun, Cong Liu, Guoping Hu, Rui Mei, Jing Shao

llms nlp benchmarks 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

arXiv Machine Learning

Jul 14

Selective Safety Steering via Value-Filtered Decoding

arXiv:2605. 14746v2 Announce Type: replace Abstract: While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints.

By Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh, Yarin Gal, Yaniv Romano

llms safety

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

One email a morning, machine-written

Related stories

Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges

CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models

Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges

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

Selective Safety Steering via Value-Filtered Decoding

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