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. Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment

    Oct 26, 2026YaJie YinLLM AbstentionRefusal Behavior in Language Models

  2. How Firm Are AI Models' Ethical Boundaries? A Pay-Stub Editing Test of 15 Models

    Oct 22, 2026Simiao Ren, Xingyu Shen, Tommy Duong +2Language Model Safety EvaluationRefusal Behavior in Language Models

  3. Faithful Latent Harm Monitors Work No Better Than the Models Own Behaviour at a Matched False Alarm Rate

    Oct 22, 2026Abhishek Mishra, Sagnik Chatterjee, Suyash ManiyarLLM Safety MonitoringLanguage Model Safety Evaluation

    University of Massachusetts Amherst

  4. WRDO: Weighted Refusal Direction Optimization in Aligned Language Models

    Oct 21, 2026Grigoriy Evseev, Vladimir Solodkin, Dmitry Bylinkin +3Refusal Behavior in Language ModelsRefusal Mechanisms in Language Models

    Moscow Independent Research Institute of Artificial Intelligence · Basic Research of Artificial Intelligence Laboratory (BRAIn Lab) · T-Technologies +1

  5. Uncensored Is Not Unbiased: Abliteration Removes Refusals but Not Script-Dependent Bias About Taiwan

    Oct 21, 2026Ju-Chun KoPolitical Bias in Language ModelsLanguage Model Bias Evaluation

    Member of Parliament, Legislative Yuan, Republic of China (Taiwan) · Adjunct Assistant Professor, Graduate Institute of Networking and Multimedia, National Taiwan University

  6. Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents

    Oct 20, 2026Ekagra Gupta, Raj Saha, Aniekan-Abasi Inyang +1LLM Agent SafetyRefusal Behavior in Language Models

    Harvard University · Clarkson University · Carleton University

  7. Concerns in Benchmarking Jailbreaks: An Empirical Study of Attack Success Rates

    Oct 19, 2026Leon Tu Nguyen, Rohan Menon, Rafael Tappe Maestro +2Jailbreak Attack EvaluationLLM Safety Benchmarks

    Carl von Ossietzky University of Oldenburg, Oldenburg, Germany · Chalmers University of Technology, Gothenburg, Sweden

  8. AfriGuard: Safety and Robust Refusal For African Languages

    Oct 19, 2026Israel Abebe Azime, Jesujoba O. Alabi, Iffat Maab +20LLM SafetyLanguage Model Safety Evaluation

    Saarland University, Saarland Informatic Campus, Germany · Masakhane NLP · National Institute of Informatics, Japan +13

  9. Receiver Decides Agent-to-Agent Negotiations

    Oct 13, 2026Fardeen Sadab, Alif Hasnain, Afsana Shehrin +2Multi-Agent NegotiationPersuasion in Language Models

    Department of Computer Science and Engineering, Islamic University of Technology, Dhaka, Bangladesh

  10. Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models

    Oct 10, 2026Seyedarmin Azizi, Erfan Baghaei Potraghloo, Arya Fayyazi +2Recurrent Language ModelsRefusal Behavior in Language Models

    University of Southern California (USC), USA

  11. Lumen-bench: Cross-Lingual Safety Gaps and the Say-Do Problem in Tool-Calling Large Language Models

    Oct 10, 2026Giovana Kerche Bonás, Thiago Laitz, Thales Sales Almeida +1LLM Safety BenchmarksLLM Safety

    Tropic AI · Maritaca AI

  12. Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning

    Oct 10, 2026Haodong Chen, Shengtao Wen, Dong Liang +2MLLM UnlearningRefusal Behavior in Language Models

    MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics · School of Intelligence Science and Technology, Nanjing University

  13. Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs

    Oct 9, 2026Zixuan Weng, Haoqi He, Weifei Jin +2Refusal Behavior in Language ModelsLanguage Model Safety Evaluation

    Georgia Institute of Technology · Independent Researcher · Duke University +1

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

    Oct 7, 2026Zhankai Ye, Yanning Wang, Yukai Jin +5Refusal Behavior in Language ModelsLLM Safety Alignment

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

  15. 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 LLMsMechanistic Interpretability

    University of Maryland, College Park

  16. On the Steering Dimensionality of Refusal in Language Models

    Oct 3, 2026Han Wang, Erik Miehling, Dennis Wei +2Language Model SteeringActivation Steering

    University of Illinois Urbana-Champaign · IBM Research

  17. PowerBench: Measuring Language Model Bias in Power-shifting Requests

    Oct 1, 2026Nicolas Martorell, Wendy Brau, Gonzalo A. Heredia +3Language Model Bias EvaluationRefusal Behavior in Language Models

    Universidad de Buenos Aires · Buenos Aires AI Safety Hub · The World Bank +1

  18. Component and Dimension Sparsity in Transformer Refusal Mechanisms

    Sep 30, 2026Vincent Siu, Glenn Grant-Richards, Vlad Pavlovich +3Refusal Behavior in Language ModelsTransformer Interpretability

    UC Santa Cruz · UCLA · UC Berkeley

  19. CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data

    Sep 29, 2026Philipp E. Glass, Alina MironLLM AuditingInstruction Tuning

    Department of Computer Science, Brunel University of London

  20. Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning

    Sep 29, 2026Jungseob Lee, Dongyub Jude Lee, Sugyeong Eo +3LLM SafetyAdversarial Robustness of Language Models

    Korea University · Zoom Communications · Yonsei University Mirae Campus

  21. Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability

    Sep 28, 2026Xu Wang, Difan Zou, Xuansheng WuLLM SycophancyLanguage Model Safety Evaluation

    The University of Hong Kong · Shenzhen Loop Area Institute · Shanghai Artificial Intelligence Laboratory

  22. Tool Mediation Alters Refusal Mechanisms in Large Language Models

    Sep 28, 2026Abel Rodríguez, Giuseppe Garofalo, Lieven Desmet +1Language Model Safety EvaluationLLM Agent Safety

    DistriNet, KU Leuven

  23. 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 ModelsJailbreak Defense

    National Taiwan University

  24. When Should a Failing Robot Ask? Initiating Corrective Human-Robot Dialogue from Audited Sensor Evidence

    Sep 18, 2026Eshika Pathak, Leela KrishnaHuman-Robot InteractionVLMs for Robotics

    University of Illinois Urbana-Champaign · Centific

  25. The Role of Fine-grained Harm Signals in LLM Safety

    Sep 16, 2026Soyeon Park, Seogyeong Jeong, Sunwoo Kim +1LLM InterpretabilityLLM Safety

    KAIST

  26. First Token Matters: Understanding Safety Collapse in Large Reasoning Models

    Sep 16, 2026Yizheng Yang, Haining Yu, Yuechen Wang +4LLM Safety AlignmentInference-Time Intervention

    Harbin Institute of Technology, Harbin, China · Guangzhou University, Guangzhou, China · City University of Macau, Macau, China

  27. When Keywords Drop but Classifiers Hold: Soft Refusals under KV Cache Compression

    Sep 16, 2026Kang Chen, Xiuze Zhou, Hong Chen +1Refusal Behavior in Language ModelsLanguage Model Safety Evaluation

    Wenzhou-Kean University · The Hong Kong University of Science and Technology (Guangzhou) · Jimei University

  28. What Drives Dialectal Jailbreaks? An Ablation of Surface Form, Cultural Framing, and Strategy Banks

    Sep 15, 2026Qingyang XuAdversarial Attacks on LLMsRefusal Behavior in Language Models

    Independent Researcher, Shanghai, China

  29. 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 EvaluationAI Agent Safety Benchmarks

    Rensselaer Polytechnic Institute · IBM Research

  30. Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families

    Sep 13, 2026Orion Reblitz-RichardsonLLM AlignmentMoral Reasoning in Language Models

    Distiller Labs.