Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration
cs.CL, cs.AI
Submitted: 2026-09-06
Updated: 2026-10-01
Comments: 33 pages, 13 figures, accepted to the EMNLP 2026 Main Conference
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- PaLM: Scaling Language Modeling with Pathways
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- OR-Bench: An Over-Refusal Benchmark for Large Language Models
- Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
- Decoding One Safety Trigger Token for Balancing Safety and Usability in Large Language Models
- Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement
- GPT-4 Technical Report
- LLaMA: Open and Efficient Foundation Language Models
- Qwen2.5 Technical Report
- Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation
- FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering