conftrace_

prompt safety

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

unsafe content detection (1) defense strategy (1) content classification (1) safety classification (1) llm safety (1) sentence encoder (1) synthetic data generation (1) weak supervision (1) evaluation methodology (1) explanation generation (1)

Papers

A Lightweight Explainable Guardrail for Prompt Safety ACL 2026 Safe-Embed: Unveiling the Safety-Critical Knowledge of Sentence Encoders ACL 2024 The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness ACL 2024