Door-in-the-Face Requests and Refusal Behaviour in Large Language Models
cs.AI, cs.CL
Submitted: 2026-09-02
Updated: 2026-09-02
Terminology
Sources
- Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
- Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
- Does Refusal Training in LLMs Generalize to the Past Tense?
- Refusal in Language Models Is Mediated by a Single Direction
- The Art of Saying No: Contextual Noncompliance in Language Models
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
- OR-Bench: An Over-Refusal Benchmark for Large Language Models
- How Reliable Is Your Jailbreak Judge? Calibration and Adversarial Robustness of Automated ASR Scoring
- Validating LLM-as-a-Judge Systems under Rating Indeterminacy
- LLMs Get Lost In Multi-Turn Conversation
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs
- Safety Alignment Should Be Made More Than Just a Few Tokens Deep
- XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
- Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
- Navigating the OverKill in Large Language Models
- Multi-lingual Multi-turn Automated Red Teaming for LLMs
- A StrongREJECT for Empty Jailbreaks
- Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection