arXiv cs.CY· Xiaohan Ding, Mengting Tu, Andrew H. Zhao, Jamie Zelazny, Candice L. Biernesser, Munmun De Choudhury·· 11 小时前AI 评分42
眼见不为知：LLM 从青少年社交媒体对话推断心理健康的认知边界
Seeing Is Not Knowing: The Epistemic Limits of LLM-Based Mental Health Inference from Youth Social Media Conversations
AI 导读
研究用 80 名有抑郁或自杀念头/行为史青少年的 Instagram 私信，评测十款推理 LLM 的心理健康推断能力，并分析 204 条推理轨迹。模型对可观察状态的推断优于对感知社会支持等主观评价的推断，结果揭示了数字痕迹在 AI 设计与评估中的认知边界：哪些可观察、哪些可合理推断、哪些必须依赖本人自述。
正文 · 原文
Abstract:Adolescents increasingly use social media for private conversations, sharing experiences and seeking support. These interactions generate digital traces, prompting efforts to infer mental health and psychosocial states. As large language models become more capable of reasoning about conversations and interpersonal dynamics, a fundamental question remains nonetheless: what can models actually "know" about an individual's psychological experience from what they are able to "see"? We evaluated ten reasoning LLMs using donated Instagram Direct Messages from 80 adolescents with a history of depression or suicidal thoughts and behaviors, comparing predictions with self-reports and analyzing 204 reasoning traces. Models performed better when inferring more observable states than participants' subjective appraisals of social experience, such as perceived social support. Beyond prediction accuracy, our findings highlight the epistemic limits of digital traces for AI design and evaluation: what can be observed, what can reasonably be inferred, and what requires people's own accounts.
| Subjects: | Human-Computer Interaction (cs.HC); Computers and Society (cs.CY) |
| Cite as: | arXiv:2611.08565 [cs.HC] |
| (or arXiv:2611.08565v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08565 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiaohan Ding [view email]
[v1]
Thu, 5 Nov 2026 16:47:06 UTC (4,490 KB)
来源：arXiv cs.CY · arxiv.org