conftrace_

false refusal

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) language model (2) llm guardrail (1) domain-specific classifier (1) vector ablation (1) refusal calibration (1) sociodemographic bia (1) persona prompting (1) inference-time intervention (1) data drift (1)

Papers

Defenses Against Prompt Attacks Learn Surface Heuristics ACL 2026 Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy ACL 2026 Challenges and Remedies of Domain-Specific Classifiers as LLM Guardrails: Self-Harm as a Case Study NAACL 2025 No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models EMNLP 2025 Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation ICLR 2025