Presents HarmAmp benchmark for multi-turn harm amplification in LLMs and TrajSafe proactive monitor that reduces harm while keeping low over-refusal and preserving capabilities.
Red Queen: Exposing Latent Multi-Turn Risks in Large Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Investigating and Alleviating Harm Amplification in LLM Interactions
Presents HarmAmp benchmark for multi-turn harm amplification in LLMs and TrajSafe proactive monitor that reduces harm while keeping low over-refusal and preserving capabilities.