EmoRSS: Mitigating Emotion-Induced Over-Refusal in Large Language Models
cs.AI
Submitted: 2026-10-04
Updated: 2026-10-04
Sources
- Inducing anxiety in large language models can induce bias
- OR-Bench: An Over-Refusal Benchmark for Large Language Models
- Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
- Measuring Massive Multitask Language Understanding
- FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment
- Large Language Models Understand and Can be Enhanced by Emotional Stimuli
- You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals
- What Matters For Safety Alignment?
- Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs
- Beyond No: Quantifying AI Over-Refusal and Emotional Attachment Boundaries
- Mitigating Exaggerated Safety in Large Language Models
- Emotion Concepts and their Function in a Large Language Model
- Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control
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
- Agents' Last Exam
- 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