Ruohao Guo
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1ML×1
Frequent co-authors
Research Timeline
2026
Investigating and Alleviating Harm Amplification in LLM Interactions
This paper introduces HarmAmp, a new benchmark for multi-turn harm amplification, and proposes TrajSafe, a proactive monitoring system that significantly reduces harmfulness in LLM interactions while maintaining usability.
Highlighted terms show continued research focus across papers