Refusal Behavior in Language Models

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

164 papers21 papers in the last four weeks, up 40% on the four weeks before. 0.2% of all new papers.

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

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

  2. 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

  3. Efficient Refusal Ablation in LLM through Optimal Transport

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

  4. When Do LLM Preferences Predict Downstream Behavior?

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

  5. Fail-Closed Alignment for Large Language Models

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

  6. Measuring and Eliminating Refusals in Military Large Language Models

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

  7. 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

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

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

  9. 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

  10. LLMs Encode Harmfulness and Refusal Separately

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