Refusal Mechanisms in Language Models

Latest papers

39 papers2 papers in the last four weeks, down 78% on the four weeks before. 0.0% of all new papers.

SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models
Oct 7, 2026Miao Yu, Hao Huang, Lu Yuan +3Refusal Mechanisms in Language Models LLM Safety Alignment
The University of Hong Kong (HKU) · Chinese Academy of Sciences (CAS) · Information Engineering University (IEU) +1
Tool Mediation Alters Refusal Mechanisms in Large Language Models
Sep 28, 2026Abel Rodríguez, Giuseppe Garofalo, Lieven Desmet +1Language Model Safety Evaluation LLM Agent Safety
DistriNet, KU Leuven
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families
Sep 13, 2026Orion Reblitz-RichardsonLLM Alignment Moral Reasoning in Language Models
Distiller Labs.
Locating and Steering Refusal Beyond Attention
Sep 4, 2026Preethi Carmel Bosco, Gopalakrishnan SrinivasanRefusal Mechanisms in Language Models Refusal Behavior in Language Models
Department of Computer Science and Engineering, Indian Institute of Technology Madras
Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models
Sep 4, 2026Minji Kim, Hyounghun KimRefusal Behavior in Language Models Refusal Mechanisms in Language Models
Graduate School of Artificial Intelligence, POSTECH · Department of Computer Science and Engineering, POSTECH
Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness
Sep 3, 2026Hoang Cuong Nguyen, Mark Dras, Usman NaseemMechanistic Interpretability Circuits in Language Models
Macquarie University, Sydney, Australia
A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals
Sep 1, 2026Yuri Son, Seunghee Kim, Hyuhng Joon Kim +1LLM Interpretability LLM Refusal Behavior
1Hanyang University · 2Samsung Electronics
You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals
Aug 31, 2026Ruoxuan Li, Pinqiao Wang, Sheng Li +1Language Model Safety Evaluation Pragmatic Reasoning in Language Models
Stony Brook University · University of Virginia
Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration
Aug 29, 2026Mohamad Zbib, Ammar MohannaRefusal Behavior in Language Models LLM Alignment
American University of Beirut
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions
Aug 29, 2026Yucheng Du, Xiyang HuLLM Abstention Refusal Mechanisms in Language Models
University of Southern California · Arizona State University
Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks
Aug 26, 2026Andrey LabunetsAdversarial Attacks on LLMs Adversarial Robustness of Language Models
UC San Diego
Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration
Aug 16, 2026Yiqi Liu, Yang Wang, Songxin Wang +2LLM Refusal Behavior Refusal Mechanisms in Language Models
University of Manchester · Shanghai University of Finance and Economics
Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoE
Aug 8, 2026Ramakrishna P. Kompella, Aadit MahajanMultilingual Language Models Mixture-of-Experts Language Models
Gödel Machines · IIT Madras
Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment
Aug 5, 2026Alina Klerings, Jannik Brinkmann, Heiner Stuckenschmidt +1Adversarial Attacks on LLMs LLM Safety Alignment
University of Mannheim · Technical University Clausthal
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
Jul 31, 2026Xinyan Guan, Jiali Zeng, Chunlei Xin +5Overthinking in Language Models RL for Language Model Reasoning
1Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences · 3Weixin AI, Tencent Inc, China
Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale
Jul 2, 2026Vadym Hadetskyi, Dario Pasquini, Artem SorokinLLM Refusal LLM Safety Alignment
Cracken AI
Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
Jul 2, 2026Thomas WinningerLLM Interpretability LLM Safety
Télécom SudParis, Évry-Courcouronnes, France · ENS Paris-Saclay, Gif-sur-Yvette, France
Addressing Over-Refusal in LLMs with Competing Rewards
Jun 30, 2026Taeyoun Kim, Aviral KumarRL for Language Model Reasoning LLM Safety
Carnegie Mellon University · SynthLabs
Refusal Lives Downstream of Persona in Chat Models
Jun 24, 2026Viola Zhong, Qirui LiLanguage Model Steering LLM Refusal Behavior
Independent · Department of Mathematics Pohang University of Science and Technology
Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP
Jun 11, 2026Elisabetta Rocchetti, Alfio FerraraLLM Refusal Behavior Causal Interventions in Language Models
Department of Computer Science, Università degli Studi di Milano, Milan, Italy · Department of Literary Studies, Philology and Linguistics, Università degli Studi di Milano, Milan, Italy
Expert-Aware Refusal Steering
Jun 2, 2026Anna C. Marbut, Daniel R. Olson, Travis J. WheelerMixture-of-Experts Language Models Language Model Steering
Department of Interdisciplinary Studies University of Montana Missoula, MT, USA · Department of Pharmacy Practice & Science University of Arizona Tucson, AZ, USA · European Bioinformatics Institute European Molecular Biology Laboratory Wellcome Genome Campus, Hinxton, United Kingdom
BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
May 28, 2026Caleb DeLeeuwLanguage Model Safety Evaluation Sparse Autoencoders
Independent researcher
Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations
May 27, 2026Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta +4LLM Jailbreak Attacks Adversarial Attacks on LLMs
University of Padua, Italy · 2Örebro University, Sweden · 3Fondazione Bruno Kessler, Italy
Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
May 26, 2026Kia-Jüng Yang, Dominik Meier, Jiachen Zhao +2Reasoning Trace Analysis LLM Refusal Behavior
University of Göttingen, Germany · LKA NRW, Germany · Northeastern University, Boston, MA, USA.
SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models
May 25, 2026Khalid Yusuf DahirLLM Safety Benchmarks Multilingual Language Model Evaluation
Independent researcher
Latent-space Attacks for Refusal Evasion in Language Models
May 20, 2026Giorgio Piras, Raffaele Mura, Fabio Brau +4Adversarial Attacks on LLMs LLM Safety
University of Cagliari · University of Genova
RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts
May 20, 2026Lukas Weidener, Marko Brkić, Mihailo Jovanović +2LLM Safety Benchmarks Language Model Safety Evaluation
Applied Scientific Intelligence, Inc.
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
May 8, 2026Hamid Kazemi, Atoosa Chegini, Maria SafiLLM Interpretability Adversarial Attacks on LLMs
Apple · Work done during an internship at Apple. Present affiliation: University of Maryland, College Park.
Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement
May 8, 2026Ying Zhang, Congyu Qiao, Xin Geng +1LLM Safety Alignment LLM Refusal Behavior
Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding
Apr 18, 2026Yupeng Qi, Ziyu Lyu, Lixin Cui +2Language Model Safety Evaluation LLM Refusal Behavior
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University · School of Information, Central University of Finance and Economics · School of Artificial Intelligence, Beijing Normal University +1

Oct 7, 2026J/K move · Enter open · S save

SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models

Miao Yu, Hao Huang, Lu Yuan, Yunpeng Li+2

The University of Hong Kong (HKU) · Chinese Academy of Sciences (CAS) · Information Engineering University (IEU)+1

Refusal Mechanisms in Language Models LLM Safety Alignment LLM Alignment LLM Interpretability Circuits in Language Models

Open paper AskPDF arXiv

Safety interpretability advances the study of Large Language Model (LLM) alignment from behavioral constraints driven by data or algorithms towards a deeper understanding of internal mechanisms. However, existing works have focused primarily on safety-related representations, attention heads, or neurons after alignment, while largely overlooking the safety mechanisms in pretrained-only models and their evolution across alignment checkpoints. To address this, we propose SafeEvo, an interpretability framework from the circuit (sparse subgraphs of an LLM) perspective. SafeEvo first applies an optimization-based extraction algorithm to identify weak refusal circuits in pretrained base LLMs that can independently express refusal behavior. Causally ablating these circuits completely eliminates the base model's refusal of harmful inputs. SafeEvo then traces the evolution of refusal circuits across successive alignment checkpoints and finds that their structures change progressively, suggesting that the alignment tax may result from refusal-circuit updates affecting utility-related parameters. To validate this, SafeEvo introduces Safety Circuit Alignment (SCA), which confines safety updates to the refusal circuits. Experiments across three LLMs and two alignment algorithms show that, on average, SCA outperforms vanilla alignment in three aspects: (1) stronger alignment, lowering harmfulness score by 63.21%; (2) less over-refusal, yielding a 58.44% decrease in refusal rates for benign queries; and (3) better utility, retaining 99.58% of the original model capabilities.