conftrace_

harmful queries

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

jailbreak attack (2) safety prompt (1) harmless helpful honest (1) refusal direction (1) inference-time defense (1) parameter removal (1) safety realignment (1) large language model (1) fine-tuned language model (1) medical vision-language model (1)

Papers

Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations EACL 2026 Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models ACL 2025 On Prompt-Driven Safeguarding for Large Language Models ICML 2024