English
Related papers

Related papers: Refusal Direction is Universal Across Safety-Align…

200 papers

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its…

Machine Learning · Computer Science 2024-11-01 Andy Arditi , Oscar Obeso , Aaquib Syed , Daniel Paleka , Nina Panickssery , Wes Gurnee , Neel Nanda

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Cryptography and Security · Computer Science 2025-09-19 Yuanbo Xie , Yingjie Zhang , Tianyun Liu , Duohe Ma , Tingwen Liu

Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and ablation. We show that this account is incomplete. Across eleven categories of refusal and…

Computation and Language · Computer Science 2026-02-03 Faaiz Joad , Majd Hawasly , Sabri Boughorbel , Nadir Durrani , Husrev Taha Sencar

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization…

Computation and Language · Computer Science 2025-11-05 Berk Atil , Rebecca J. Passonneau , Fred Morstatter

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing scientific interest in mechanistic interpretability, recent work encoded refusal behavior as a…

Artificial Intelligence · Computer Science 2026-03-25 Giorgio Piras , Raffaele Mura , Fabio Brau , Luca Oneto , Fabio Roli , Battista Biggio

The safety alignment of large language models (LLMs) can be circumvented through adversarially crafted inputs, yet the mechanisms by which these attacks bypass safety barriers remain poorly understood. Prior work suggests that a single…

Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior across six LLMs from…

Computation and Language · Computer Science 2025-01-15 Fabian Hildebrandt , Andreas Maier , Patrick Krauss , Achim Schilling

Large Language Models' safety-aligned behaviors, such as refusing harmful queries, can be represented by linear directions in activation space. Previous research modeled safety behavior with a single direction, limiting mechanistic…

Computation and Language · Computer Science 2025-05-28 Wenbo Pan , Zhichao Liu , Qiguang Chen , Xiangyang Zhou , Haining Yu , Xiaohua Jia

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem…

Artificial Intelligence · Computer Science 2026-03-13 Zhiyu Xue , Zimo Qi , Guangliang Liu , Bocheng Chen , Ramtin Pedarsani

While large language models (LLMs) have increasingly been applied to hate speech detoxification, the prompts often trigger safety alerts, causing LLMs to refuse the task. In this study, we systematically investigate false refusal behavior…

Computation and Language · Computer Science 2026-01-14 Kyuri Im , Shuzhou Yuan , Michael Färber

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

Computation and Language · Computer Science 2026-04-21 Yuheng Chen , Zhiyu Wu , Bowen Cheng , Tetsuro Takahashi

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Cryptography and Security · Computer Science 2026-01-28 Yangyang Guo , Ziwei Xu , Si Liu , Zhiming Zheng , Mohan Kankanhalli

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify…

Computation and Language · Computer Science 2025-05-30 Wei Jie Yeo , Nirmalendu Prakash , Clement Neo , Roy Ka-Wei Lee , Erik Cambria , Ranjan Satapathy

Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemble harmful instructions. A natural approach is to ablate the global refusal direction,…

Computation and Language · Computer Science 2026-05-29 Utsav Maskey , Mark Dras , Usman Naseem

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Computation and Language · Computer Science 2025-10-01 Yuyou Zhang , Miao Li , William Han , Yihang Yao , Zhepeng Cen , Ding Zhao

Safety guardrails in large language models(LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to…

Computation and Language · Computer Science 2025-11-03 Adel Khorramrouz , Sharon Levy

Large Language Models (LLMs) are widely used across sectors, yet their alignment with International Humanitarian Law (IHL) is not well understood. This study evaluates eight leading LLMs on their ability to refuse prompts that explicitly…

Computers and Society · Computer Science 2025-06-10 John Mavi , Diana Teodora Găitan , Sergio Coronado

Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures a complementary failure mode: denial of assistance to…

Cryptography and Security · Computer Science 2026-03-12 David Campbell , Neil Kale , Udari Madhushani Sehwag , Bert Herring , Nick Price , Dan Borges , Alex Levinson , Christina Q Knight

Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…

Computation and Language · Computer Science 2025-10-28 Havva Alizadeh Noughabi , Julien Serbanescu , Fattane Zarrinkalam , Ali Dehghantanha
‹ Prev 1 2 3 10 Next ›