conftrace_

harmfulness detection

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) jailbreak attack (2) context-aware evaluation (1) safety generalization (1) jailbreak prevention (1) representation router (1) intermediate hidden state (1) safety reasoning (1) safe generation (1) multi-agent system (1)

Papers

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router ACL 2026 MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models EMNLP 2025 SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025 Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis EMNLP 2024