Story
arxiv_cs_cl · Nov 4, 2026 · paper
Source brief
Measuring Risk, Not Harm: Detecting Psychological Harm Risk Factors in LLM Conversations
arxiv.orgNov 4, 2026
original source linked
In brief
Psychological harms from interactions with large language models cannot be monitored directly because they may emerge over repeated interactions and depend strongly on subjective individual user context. We propose me...
Feed lens
evaluation