MentalLoom 评估：LLM 在模糊社交情境下的心理解读偏好与确信度

Reading Too Much Into It? Interpretive Preferences and Commitment in LLM Mentalisation under Ambiguity

AI 导读

研究团队提出 MentalLoom，用 604 个模糊社交情境、匹配的抑郁与社交焦虑自我披露及四轮对话，评估 LLM 的心理解读能力。在八个 LLM 上，自我披露最初引发更负面的解释，但对叙述者的解读更偏正面；脚本化重复提问会带来更强的情感支持、更正的叙述者导向认同和更高确定性，而事件证据并未增加。

正文 · 原文

View PDF HTML (experimental)

Abstract:Large Language Models (LLMs) are increasingly used for interpersonal advice, potentially shaping how users interpret ambiguous social encounters. Existing Theory of Mind evaluations typically rely on predefined answers, while uncertainty research overlooks LLMs' preferred explanations and confidence under psychological distress. To address these gaps, we introduce MentalLoom, a novel evaluation of LLM mentalisation comprising 604 ambiguous social episodes, matched depression and social anxiety disclosures, and four-turn dialogues with unchanged event evidence. Across eight LLMs, disclosures initially elicited more negative explanations overall but more positive narrator-directed interpretations. Scripted repeated questioning showed greater emotional support, stronger positive narrator-directed endorsement, and higher certainty without new event evidence. These findings show that user context can reshape interpretive preferences and commitment while the underlying ambiguity remains unresolved.

Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.28105 [cs.CL]
	(or arXiv:2610.28105v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.28105 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Stephanie Fong [view email]
[v1] Tue, 20 Oct 2026 12:18:11 UTC (2,573 KB)

来源：arXiv cs.CL · arxiv.org