arXiv Computation and Language September 23, 2026 By Zixuan Wang, Bingjie Zhang, He Zhao, Dandan Guo

Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibratione

Read the original on arXiv Computation and Language →

The paper addresses the problem of over‑refusal in safety‑aligned large language models, where benign instructions are incorrectly rejected. It identifies that a small set of hypersensitive safety heads in transformer attention misfire on hard‑safe prompts, causing abnormal attention entanglement and high‑entropy routing conflicts that block necessary attention to target entities. To mitigate this, the authors propose Semantic Routing Calibration (SRC), a lightweight, training‑free inference framework that dynamically suppresses these hypersensitive heads and fuses logits from dual branches to restore trustworthy reasoning while preserving intrinsic safety performance.

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 Computation and Language.

arXiv AI

2d ago

Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration

arXiv:2609.25049v2 Announce Type: replace-cross Abstract: Large language models (LLMs) aligned for safety often suffer from over-refusal, incorrectly rejecting benign yet safety-related instructions....

By Zixuan Wang, Bingjie Zhang, He Zhao, Dandan Guo

llms safety

arXiv Machine Learning

Jun 2

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing

arXiv:2606. 00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts.

By Maryam Hashemzadeh, Jerry Huang, Minseon Kim, Marc-Alexandre C\^ot\'e, Sarath Chandar

llms fine-tuning benchmarks safety

arXiv Machine Learning

Aug 14

HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models

arXiv:2608. 12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks.

By Fangzhou Chen, Shiji Zhao, Mengyang Wang, Qihui Zhu, Ranjie Duan, Maoxun Yuan, Xingxing Wei

llms rag benchmarks 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

arXiv AI

Sep 2

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

arXiv:2609.00051v1 Announce Type: cross Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the...

By Kuan-Lin Chu, Chung-En Sun, Tsui-Wei Weng

llms 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

One email a morning, machine-written

Related stories

Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing

HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models

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

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

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