Refusal Behavior in Language Models

Ask about this topic

Overview

This field studies when language models refuse, comply, or abstain, and whether those decisions reflect harmfulness, uncertainty, or learned policy cues. Researchers use safety fine-tuning and preference or reinforcement learning, alongside activation steering, circuit analysis, and runtime guards that monitor or redirect responses. Benchmarks test the balance between refusing harmful requests and answering benign ones across languages, formats, modalities, and multi-turn or tool-using settings. A central challenge is making refusals robust to jailbreaks without causing over-refusal, while recognizing that detecting risk and actually refusing may rely on different mechanisms.

Latest papers

CardsList

148 papers21 papers in the last four weeks, down 16% on the four weeks before. 0.1% of all new papers.

  1. The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment

    Apr 13, 2026Shasha Yu, Fiona Carroll, Barry L. BentleyLLM Agent EvaluationTool-Using Language Agents

    Cardiff School of Technologies, Cardiff Metropolitan University, Cardiff, Wales CF5 2YB, UK · School of Professional Studies, Clark University, Worcester, MA 01610 USA · Harvard Medical School, Harvard University, Boston, MA 02115 USA

  2. What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal

    Apr 9, 2026Stephen Cheng, Sarah Wiegreffe, Dinesh ManochaLanguage Model SteeringLLM Interpretability

    University of Maryland, College Park

  3. How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

    Apr 6, 2026Gregory N. FrankLLM InterpretabilityLLM Safety

    Chief Scientist, Molt AI Corp.

  4. Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules

    Apr 3, 2026Cameron Pattison, Lorenzo Manuali, Seth LazarRefusal Behavior in Language ModelsRefusal Mechanisms in Language Models

    Department of Philosophy, Vanderbilt University · Department of Philosophy, University of Michigan · School of Government and Policy, Johns Hopkins University

  5. CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders

    Apr 2, 2026Su-Hyeon Kim, Hyundong Jin, Yejin Lee +1Refusal Behavior in Language ModelsMechanistic Interpretability

    Yonsei University, Seoul, Republic of Korea

  6. One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety

    Apr 1, 2026Samee Arif, Naihao Deng, Zhijing Jin +1LLM Jailbreak AttacksLanguage Model Safety Evaluation

    University of Michigan · University of Toronto

  7. Do Language Models Know When They'll Refuse? Probing Introspective Awareness of Safety Boundaries

    Mar 31, 2026Tanay GondilLanguage Model IntrospectionRefusal Behavior in Language Models

    Purdue University

  8. Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs

    Mar 29, 2026Utsav Maskey, Mark Dras, Usman NaseemLLM InterpretabilityLLM Refusal Behavior

    Macquarie University

  9. Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

    Mar 24, 2026Wenyu Chen, Xiangtao Meng, Chuanchao Zang +6LLM SecurityLLM Jailbreak Attacks

    Shandong University

  10. On the Failure of Topic-Matched Contrast Baselines in Multi-Directional Refusal Abliteration

    Mar 23, 2026Valentin PetrovRefusal Behavior in Language ModelsCausal Interventions in Language Models

    INMECHA INC, San Francisco

  11. Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models

    Mar 23, 2026Hyundong Jin, Dongyoon Han, Eunwoo KimVLM UnlearningMachine Unlearning

    Chung-Ang University · NAVER AI Lab

  12. Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails

    Mar 18, 2026Gregory N. FrankLanguage Model Safety EvaluationRefusal Behavior in Language Models

    Independent Researcher

  13. Literary Narrative as Moral Probe : A Cross-System Framework for Evaluating AI Ethical Reasoning and Refusal Behavior

    Mar 13, 2026David C. FlynnMoral Reasoning in Language ModelsAI Safety Evaluation

  14. Hallucination as output-boundary misclassification: a composite abstention architecture for language models

    Mar 12, 2026Angelina HintsanenLLM Hallucination MitigationHallucination in Language Models

    NEXUS Laboratory, Helsinki, Finland

  15. Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment

    Mar 12, 2026Zhiyu Xue, Zimo Qi, Guangliang Liu +2LLM Safety AlignmentOver-Refusal

    University of California, Santa Barbara · Johns Hopkins University · Michigan State University +1

  16. From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions

    Mar 9, 2026Rishab Alagharu, Ishneet Sukhvinder Singh, Shaibi Shamsudeen +2Language Model SteeringLLM Refusal Behavior

    Algoverse AI Research · Carnegie Mellon University · University of Maryland

  17. Efficient Refusal Ablation in LLM through Optimal Transport

    Mar 4, 2026Geraldin Nanfack, Eugene Belilovsky, Elvis DohmatobAdversarial Attacks on LLMsJailbreak Attacks

    Concordia University, Montreal, Canada · Mila – Quebec AI Institute, Montreal, Canada

  18. Residual Stream Analysis of Overfitting And Structural Disruptions

    Mar 4, 2026Quan Liu, Han Zhou, Wenquan Wu +2Safety-Preserving Fine-Tuning of Language ModelsRefusal Behavior in Language Models

    BUPT · Baidu

  19. LSR: Linguistic Safety Robustness Benchmark for Low-Resource West African Languages

    Feb 27, 2026Godwin Abuh FarunaLLM Safety BenchmarksLanguage Model Safety Evaluation

    Fagmart Lab

  20. When Do LLM Preferences Predict Downstream Behavior?

    Feb 21, 2026Katarina Slama, Alexandra Souly, Dishank Bansal +3LLM Decision-MakingPreference Alignment

    UK AI Security Institute

  21. Fail-Closed Alignment for Large Language Models

    Feb 19, 2026Zachary Coalson, Beth Sohler, Aiden Gabriel +1LLM AlignmentRefusal Behavior in Language Models

    Oregon State University, Corvallis, OR USA.

  22. Measuring and Eliminating Refusals in Military Large Language Models

    Feb 18, 2026Jack FitzGerald, Dylan Bates, Aristotelis Lazaridis +17Refusal Behavior in Language ModelsLLM Refusal Behavior

    EdgeRunner AI.

  23. A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models

    Feb 17, 2026Noa Linder, Meirav Segal, Omer Antverg +5LLM Refusal BehaviorRefusal Behavior in Language Models

    Irregular · University of Zurich

  24. There Is More to Refusal in Large Language Models than a Single Direction

    Feb 2, 2026Faaiz Joad, Majd Hawasly, Sabri Boughorbel +2LLM InterpretabilityLLM Refusal Behavior

    Qatar Computing Research Institute, HBKU, Doha, Qatar

  25. Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation

    Nov 14, 2025Mohamad Amin Mohamadi, Tianhao Wang, Zhiyuan LiLLM AbstentionLLM Hallucination Mitigation

    Toyota Technological Institute at Chicago · University of California, San Diego

  26. The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs

    Oct 15, 2025Pardis Sadat Zahraei, Gokhan Tur, Dilek Hakkani-Tür +1LLM AlignmentRefusal Behavior in Language Models

    University of Illinois Urbana-Champaign (UIUC) · Qatar Computing Research Institute (QCRI), Hamad Bin Khalifa University

  27. LLMs Encode Harmfulness and Refusal Separately

    Jul 16, 2025Jiachen Zhao, Jing Huang, Zhengxuan Wu +2LLM InterpretabilityLLM Refusal Behavior

    Northeastern University · Stanford University

  28. Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness

    Jun 30, 2025Tung-Ling Li, Hongliang LiuLLM AlignmentLanguage Model Safety Evaluation

    Palo Alto Networks