arXiv AI October 31, 2026 By Chao Chen, Pengyang Shao, Wei Qin, Shijie Hao, Fei Shen, Richang Hong

Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective

The paper investigates why safety‑aligned large language models still over‑refuse harmless queries, attributing the issue to overlapping representations in deeper layers and imbalanced gradient coupling that favors refusal. It proposes GOAL, a framework that orthogonalizes over‑refusal gradients against a low‑rank refusal subspace and adds contrastive learning to sharpen harmful‑vs‑over‑refusal representation separation. Experiments show GOAL reduces over‑refusal while maintaining safety and general 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 AI.

arXiv AI

Aug 13

Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models

arXiv:2608. 11583v1 Announce Type: new Abstract: Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be concentrated in a smaller set of parameters.

By Mingyu Zong, Sampad Mohanty, Bhaskar Krishnamachari

llms benchmarks safety

Hugging Face Trending Papers

Jun 17

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.

llms benchmarks safety

arXiv Machine Learning

Jul 13

Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal

arXiv:2607. 08883v1 Announce Type: new Abstract: Behavioral alignment in large language models often masks fragile internal safety representations.

By Ege \c{C}akar, Hannah Guan, Kayden Kehe

llms safety

arXiv AI

Aug 24

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs

arXiv:2605.01913v2 Announce Type: replace-cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vul...

By Sadia Asif, Mohammad Mohammadi Amiri

llms fine-tuning benchmarks safety

arXiv AI

23h ago

Compositional Unalignment: Auditing Safety in Large Vision-Language Models

arXiv:2611.07216v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) are vulnerable to compositional harm: an image and a prompt that are benign in isolation become harmful through...

By Hong kyu Lee, Kai Shu, Li Xiong

llms fine-tuning multimodal benchmarks 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

One email a morning, machine-written

Related stories

Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs

Compositional Unalignment: Auditing Safety in Large Vision-Language Models

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