conftrace_

positive prompt

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

energy-based detection (1) negative prompt (1) story completion (1) large language model (1) prompt injection (1) adversarial prompt (1) jailbreak attack (1) vision-language model (1) out-of-distribution detection (1) semantic knowledge (1)

Papers

Out-of-Distribution Detection with Positive and Negative Prompt Supervision Using Large Language Models AAAI 2026 Dagger Behind Smile: Fool LLMs with a Happy Ending Story EMNLP 2025