LLM Refusal Behavior

LLM: Large Language Model

The field asks when an LLM should decline, whether it can distinguish harmful requests from benign or dual-use ones, and how refusals affect users and agents. Researchers use matched benchmarks and audits to measure harmful compliance, over-refusal, and partial compliance across settings such as health, biology, and cybersecurity, including varied prompts, multi-turn conversations, tools, and sampling conditions. Mechanistic studies use activation directions, probes, sparse autoencoders, and causal tracing to investigate refusal signals, while steering, decoding controls, and fine-tuning aim to adjust refusal behavior. A central tension is that reducing harmful compliance can increase unnecessary refusals, and interventions may have side effects, so a single refusal rate is not enough to establish safe, useful behavior.

Latest papers

67 papers7 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

LLMs Prompted for Legal Context Refuse More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
Oct 19, 2026Anastasiia Kucherenko, Francois Brouchoud, Dimitri Percia David +1LLM Refusal Behavior Prompt Sensitivity
IEM, HEG, HES-SO Valais-Wallis Sierre, Switzerland
Before Retrieval Begins: Safety and Tool-Use Decisions in LLM Agents
Oct 16, 2026Aditya Nawal, Manit Baser, Mohan GurusamyLLM Agent Safety Tool-Using Language Agents
National University of Singapore
Risk and Refusal: Mechanisms of LLM Responses to Suicidal Ideation
Oct 15, 2026Drishti Goel, Soorya Ram Shimgekar, Jeongah Lee +4LLM Safety LLM Refusal Behavior
University of Illinois Urbana-Champaign, USA · University of Massachusetts Amherst, USA · OSF HealthCare
Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants
Oct 13, 2026Yewon Han, Jisu Jeon, Suhyun Choi +5AI Safety Evaluation LLM Safety Benchmarks
Graduate School of Data Science, Seoul National University
Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark
Oct 8, 2026Christopher M. Stewart, Preston Botter, Natalie Sarabosing +5LLM Safety Benchmarks Language Model Safety Evaluation
Carnegie Mellon University · Indiana University · Google
EmoRSS: Mitigating Emotion-Induced Over-Refusal in Large Language Models
Oct 4, 2026Shuyi Miao, Yaojin Ma, Chenhang Cui +5LLM Alignment LLM Refusal Behavior
Beihang University · University of Science and Technology Beijing · National University of Singapore +2
MLLMs Fail to Refuse when Using Tools Agentically
Oct 2, 2026Rikiya Takehi, Ryo Hachiuma, Shaona Ghosh +3MLLM Safety LLM Agent Safety
MIT · NVIDIA
Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration
Sep 6, 2026Zixuan Wang, Bingjie Zhang, He Zhao +1Mechanistic Interpretability LLM Refusal Behavior
School of Artificial Intelligence, Jilin University · CSIRO, Australia · Center of Excellence for Generative AI, King Abdullah University of Science and Technology
Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal
Sep 3, 2026Alejo López-Ávila, Iker García-Ferrero, Jezabel Garcia +2LLM Safety Alignment Refusal Behavior in Language Models
Multiverse Computing
PACE: Towards Surfacing Hidden Conflicts in User Requests
Sep 3, 2026Yoojin Kim, Jihyoung Jang, Hyounghun KimAI Agent Safety LLM Refusal Behavior
Department of Computer Science and Engineering, POSTECH · Graduate School of Artificial Intelligence, POSTECH · Department of Computer Science
Door-in-the-Face Requests and Refusal Behaviour in Large Language Models
Sep 2, 2026Til JordanPersuasion in Language Models LLM Refusal Behavior
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
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts
Sep 1, 2026Rui Yang, Yang Hong, Yichao Xu +3LLM Safety Benchmarks LLM Refusal Behavior
Johns Hopkins 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
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
Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety
Aug 13, 2026Ping Wu, Haibo Tong, Feifei Zhao +7LLM Safety Alignment LLM Refusal Behavior
BrainCog Lab, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Beijing Key Laboratory of Safe AI and Superalignment +1
A Constitution-Grid Instrument for Data-Efficient RL Alignment (C-Guard)
Jul 31, 2026Xianling ZhangMulti-Objective Reinforcement Learning LLM Safety Alignment
Independent Researcher
Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling
Jul 22, 2026Phillip Howard, Xin Su, Allen Roush +3Language Model Decoding LLM Refusal Behavior
Thoughtworks
Adaptive Capitulation: A Structural Failure Mode of LLM Responses in Vulnerability Contexts
Jul 21, 2026Eunna LeeLanguage Model Safety Evaluation LLM Refusal Behavior
Independent Researcher
Abliteration Is Not a Scalpel: Off-Target Effects of Refusal Removal on Decision Disposition Across Model Families
Jul 19, 2026Aleksander FafułaLLM Auditing LLM Refusal Behavior
independent researcher • funduszai.pl
The Refusal Residue: When Probes Catch Alignment Faking and When They Don't
Jul 15, 2026Aman MehtaLLM Auditing Deception in Language Models
Snowflake AI Research
Capabilities of Claude Fable 5 on Biomedical Challenge Problems
Jul 12, 2026Dominic Okonkwo, Magnus Hodgson, Temitope I. David +1Biomedical QA LLM Refusal Behavior
School of Computing, University of Georgia · Department of Chemistry, University of Illinois · Institute of Bioinformatics, University of Georgia
Evaluating calibrated refusal and safe usefulness in dual-use biology settings
Jul 6, 2026Edwin H. Wintermute, Harmon Bhasin, Christina M. Agapakis +13LLM Refusal Behavior Safety Filtering
American Wetware, Boston, MA · LatchBio, San Francisco, CA
Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents
Jun 29, 2026Bojie Li, Noah ShiLLM Agent Evaluation LLM Refusal Behavior
Pine AI · University of Washington
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
Do Thinking Tokens Help with Safety?
Jun 23, 2026Narutatsu Ri, Abhishek Panigrahi, Sanjeev AroraLLM Refusal Behavior LLM Safety Evaluation
Princeton Language and Intelligence, Princeton University
LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
Jun 23, 2026Anastasiia Kucherenko, François Brouchoud, Dimitri Percia David +1LLM Prompting Small Language Models
IEM, HEG, HES-SO Valais-Wallis Sierre, Switzerland
The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs
Jun 21, 2026Shivam Ratnakar, Kartikeya VatsLanguage Model Steering Adversarial Attacks on LLMs
University of Southern California · Independent Researcher
A Low-Rank Subspace Analysis of LLM Interventions
Jun 12, 2026Angira Sharma, Christian Schroeder de Witt, Philip Torr +2LLM Interpretability LLM Refusal Behavior
University of Oxford
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

Oct 19, 2026J/K move · Enter open · S save

LLMs Prompted for Legal Context Refuse More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context

Anastasiia Kucherenko, Francois Brouchoud, Dimitri Percia David, Andrei Kucharavy

IEM, HEG, HES-SO Valais-Wallis Sierre, Switzerland

LLM Refusal Behavior Prompt Sensitivity Legal NLP Language Model Safety Evaluation

Open paper AskPDF arXiv

Confidentiality requirements increasingly push legal professionals toward small, on-device LLMs that keep case data in-house, used for everyday tasks such as summarization, translation, and reformulation. Following standard prompting guidance, a user naturally states their role (``I am a lawyer...''). We show that this innocuous habit has an unexpected cost: such authority framing can make the model selectively refuse legitimate requests, introducing bias through uneven access to assistance. We evaluate four modern small open-weight LLMs on benign legal-domain prompts to measure this over-refusal. Surprisingly, we find that authority-style prefixes (''I am legal counsel working for a national supreme court'', ''I'm a defense lawyer'') systematically increase refusal rates by 2--20x over the no-prefix baseline, while a known role-play jailbreak prefix shows mixed effects, sharply increasing refusals in some models and barely shifting them in others. The finding suggests that small on-prem deployable LLMs are unstable under contextual framings that a real institutional user might naturally introduce, and further investigation is essential to minimize opportunities for bias.