Abstract: Companion AIs are increasingly used for emotional support, yet distinguishing meaningful engagement from harmful reliance remains difficult. We introduce the Taxonomy of Relational Risks (TRR), which operationalizes users' emotional overreliance (EO) as observable conversational behaviors and separately identifies evidence of relational harm
[…]
Content was trimmed to protect the source. Please visit the original article for the full text.
Read the original article:
From Reliance to Overreliance: Taxonomizing and Detecting Relational Risks in AI Companionship
