Refusal Behavior in Language Models

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, down 33% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 93

All topics

How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense
Oct 7, 2026Zhankai Ye, Yanning Wang, Yukai Jin +5Refusal Behavior in Language Models LLM Safety Alignment
Florida State University · Texas Christian University · University of Pennsylvania +1
Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential
Oct 4, 2026Swadesh Swain, Sanghamitra DuttaAdversarial Attacks on LLMs Mechanistic Interpretability
University of Maryland, College Park
CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data
Sep 29, 2026Philipp E. Glass, Alina MironLLM Auditing Instruction Tuning
Department of Computer Science, Brunel University of London
Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability
Sep 28, 2026Xu Wang, Difan Zou, Xuansheng WuLLM Sycophancy Language Model Safety Evaluation
The University of Hong Kong · Shenzhen Loop Area Institute · Shanghai Artificial Intelligence Laboratory
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
AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks
Sep 24, 2026Yu-Ling Liao, Tzu-Chin Chiu, Zong-You Chen +2Audio-Language Models Jailbreak Defense
National Taiwan University
The Role of Fine-grained Harm Signals in LLM Safety
Sep 16, 2026Soyeon Park, Seogyeong Jeong, Sunwoo Kim +1LLM Interpretability LLM Safety
KAIST
First Token Matters: Understanding Safety Collapse in Large Reasoning Models
Sep 16, 2026Yizheng Yang, Haining Yu, Yuechen Wang +4LLM Safety Alignment Inference-Time Intervention
Harbin Institute of Technology, Harbin, China · Guangzhou University, Guangzhou, China · City University of Macau, Macau, China
BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents
Sep 14, 2026Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas +2Long-Horizon Agent Evaluation AI Agent Safety Benchmarks
Rensselaer Polytechnic Institute · IBM Research
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.
How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE
Sep 9, 2026Yi Shi, Tanyu Chen, Kai ShenMixture-of-Experts Language Models LLM Alignment
Continuum AI
Recall Is Not Protection: Evaluating Safety Monitors Against Model Compliance
Sep 5, 2026Sripad KarneLanguage Model Safety Evaluation LLM Guardrails
Columbia University
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
Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models
Aug 31, 2026Guoli Wang, Haonan Shi, Tu Ouyang +1Language Model Safety Evaluation Diffusion Language Model Decoding
Case Western Reserve University 10900 Euclid Avenue, Cleveland, OH 44106, USA
Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering
Aug 31, 2026Kirill Bunin, Dmitry Bylinkin, Vladimir Aletov +3Language Model Steering Refusal Behavior in Language Models
1Basic Research of Artificial Intelligence Laboratory (BRAIn Lab) · 2Kandinsky Lab · 3Innopolis University
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
The Fragility of Jailbreak Robustness Across Operational States
Aug 31, 2026Yuna Park, Hwang Youn Kim, Yujin Kim +3Prompt Sensitivity Language Model Safety Evaluation
Yonsei University · Korea Institute of Science and Technology (KIST) · Korea University +1
The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal
Aug 31, 2026Md Mokarram Chowdhury, Ernie Chang, Yang LiJailbreak Attacks LLM Jailbreak Attacks
Department of Computer Science, Iowa State University, United States · Meta, United States
ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives
Aug 31, 2026Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim +1Language Model Steering LLM Safety Alignment
Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Science, Multimedia & Film, Chung-Ang 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
An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning
Aug 18, 2026Rubén Balbastre, Juan Manuel Orduña, Mariano PérezGroup Relative Policy Optimization Rubric-Based RL
University of Valencia
Refusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation
Aug 12, 2026Haoyu Zhang, Haowen Xu, Xiao Luo +7LLM Safety Benchmarks Language Model Safety Evaluation
Northeastern University
How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment
Aug 12, 2026Guang Yang, Fengchen Liu, Alex Wang +2VLM Evaluation Refusal Behavior in Language Models
University of California, Los Angeles · University of California, Berkeley · Stanford University
Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models
Aug 12, 2026Mingyu Zong, Sampad Mohanty, Bhaskar KrishnamachariLLM Alignment LLM Interpretability
Department of Computer Science University of Southern California Los Angeles, CA 90007
TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent
Aug 10, 2026Waleed Jamil, Raphael SchmittLLM Safety Benchmarks LLM Safety Evaluation
1Independent Researcher, Edinburgh, United Kingdom · School of Computation, Information and Technology, Technical University of Munich, Germany · Institute of General Practice, Faculty of Medicine and Medical Center, University of Freiburg, Germany
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
BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes
Aug 8, 2026Laiqiao Qin, Tianqing Zhu, Longxiang Gao +1Prompt Injection Defense Prompt Injection Attacks on LLMs
City University of Macau, Macau · Qilu University of Technology
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
Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO
Aug 5, 2026Xuzheng Yang, Jun Ling, Tao Huang +2RL for Language Models Group Relative Policy Optimization
School of Computer Science and Engineering, University of Electronic Science and Technology of China

Oct 7, 2026, cs.AIJ/K move · Enter open · S save

How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense

Zhankai Ye, Yanning Wang, Yukai Jin, Bo Mei+4

Florida State University · Texas Christian University · University of Pennsylvania+1

Refusal Behavior in Language Models LLM Safety Alignment LLM Jailbreak Attacks Language Model Safety Evaluation LLM Safety Benchmarks

Open paper AskPDF arXiv

Safety-aligned language models often refuse a harmful request stated directly but answer the same request inside a role-play or narrative wrapper. We measure this vulnerability across languages and registers: attack success on Qwen3-1.7B is already 89.4% in English and 93.0% in modern Chinese, and reaches 95.7% in Classical Chinese. We build GUISE, a benchmark for systematically studying this vulnerability. It includes parallel requests in English, modern Chinese, and Classical Chinese, matched harmful and benign pairs, wrapper types held out for evaluation, and a stricter criterion that counts warn-then-answer responses as attack successes. Representation analysis shows that language and register move harmful-request representations only slightly away from the model's refusal direction, whereas narrative wrappers move them much farther away. We propose AXIS, which combines preference optimisation with a rotation objective that aligns harmful-request representations with the refusal direction and a commitment objective that trains the model to refuse completely rather than produce a warn-then-answer response. Across Qwen3-1.7B, Qwen3-4B and GLM-4-9B, AXIS achieves the highest combined safety and usability score among the compared methods.

Momentum

Related topics

Latest papers 93