跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.25734 · v1

From Reliance to Overreliance: Taxonomizing and Detecting Relational Risks in AI Companionship

首次提交 2026-11-19 16:46
版本更新 2026-11-19 16:46
雷达观测 2026-11-20 19:58
arXiv ↗PDF ↗

摘要

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 (RH), enabling empirical examination of when reliance behaviors co-occur with adverse consequences. Using naturalistic Character.AI and Replika conversations from 110 adults, we found EO-related behaviors in 63.2% of non-roleplay conversations, while observable relational harms appeared in 10.5%. Although EO did not necessarily lead to harm, recurring patterns often co-occurred with harmful outcomes, suggesting value as risk indicators. Open-source LLMs satisfactorily detected 12 of 14 EO behaviors in at least one configuration. Qualitative analysis revealed expectations of care, repeated support seeking, dependency, distress, and reduced confidence in personal judgment. We argue for graduated safety interventions tailored to patterns and trajectories of EO-related behavior.

作者备注:42 pages

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 16:46 · 最新观测版本

From Reliance to Overreliance: Taxonomizing and Detecting Relational Risks in AI Companionship

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 (RH), enabling empirical examination of when reliance behaviors co-occur with adverse consequences. Using naturalistic Character.AI and Replika conversations from 110 adults, we found EO-related behaviors in 63.2% of non-roleplay conversations, while observable relational harms appeared in 10.5%. Although EO did not necessarily lead to harm, recurring patterns often co-occurred with harmful outcomes, suggesting value as risk indicators. Open-source LLMs satisfactorily detected 12 of 14 EO behaviors in at least one configuration. Qualitative analysis revealed expectations of care, repeated support seeking, dependency, distress, and reduced confidence in personal judgment. We argue for graduated safety interventions tailored to patterns and trajectories of EO-related behavior.

查看此版本解读 →查看此版本原文 ↗