arXiv cs.CL· Junkai Zhou, Shiting Guan, Zhaoyi Zhang·· 11 小时前AI 评分34
基于成人依恋理论评估 LLM 情感陪伴能力：ECBench 基准发布
Who Is Your Ideal Companion? Evaluating Emotional Companion Capabilities of LLMs Based on Adult Attachment Theory
AI 导读
研究团队将成人依恋理论引入 LLM 评估，用 ECR-R 量表刻画依恋焦虑与回避，并提出情感陪伴基准 ECBench，覆盖情感支持、协作任务、冲突解决、社交引导四类场景，横跨友谊与恋爱关系。ECBench 采用 11 项对话质量指标和三种评估方法，对 32 个 LLM 的依恋倾向进行了测评，并选取代表性模型考察其在多轮情境交互中的表现及提示词能否塑造这些倾向。
正文 · 原文
Abstract:As large language models (LLMs) are increasingly applied for emotional companionship, evaluating their behavior and capabilities in intimate relationships has become a pressing issue. However, existing assessments primarily characterize general personality traits, providing limited insight into model behavior within intimate and emotionally sensitive contexts. Therefore, we introduce adult attachment theory into LLM evaluation and use the Experiences in Close Relationships-Revised (ECR-R) scale to characterize attachment anxiety and avoidance. To evaluate emotional companionship capabilities of LLMs in realistic interaction scenarios, we present an emotional companionship benchmark, ECBench, spanning four scenarios including emotional support, collaborative tasks, conflict resolution, and social guidance, across friendship and romantic relationships. ECBench is utilized to assess model behavior using 11 dialogue-quality metrics and three evaluation methods. We evaluate the attachment tendencies of 32 LLMs and select representative models to investigate how these tendencies manifest in contextualized multi-turn interactions and whether they can be shaped through prompting. Our study provides a theoretical lens from psychology, along with practical tools to understand and select LLMs for emotional companionship.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.13168 [cs.CL] |
| (or arXiv:2608.13168v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.13168 arXiv-issued DOI via DataCite |
Submission history
From: Junkai Zhou [view email]
[v1]
Thu, 13 Aug 2026 12:32:33 UTC (414 KB)
[v2]
Wed, 4 Nov 2026 02:45:35 UTC (418 KB)
来源：arXiv cs.CL · arxiv.org