让大模型学会识别情绪对话中关键认知评估维度。
Why It Hurts: Identifying the Drivers of Negative Thoughts in Emotional Support Conversations
- 基于贝叶斯逆规划构建多智能体框架，动态推断上下文相关的评估维度。
- 在996条对话上验证，小模型提升幅度达23.7%，大模型提升15.2%。
- 适合做心理支持系统研发或认知行为干预研究的团队使用。
大语言模型（LLMs）在情绪支持任务中日益普及，例如负面思维重构。该任务依赖于修改认知评估——对引发负面情绪事件的主观解读，通常被划分为多个离散维度。现有基于LLM的框架通过全面评估所有可能维度来建模认知评估，但未能考虑不同情境下各维度的显著性差异。本文探究一个被忽视的核心问题：'LLMs能否从情绪支持对话中推断出显著的认知评估维度？' 为此，我们构建了AppraiSal基准，包含996条经人工标注心理状态的情绪支持对话，涵盖显著的认知评估维度。同时提出PRISM，一种基于贝叶斯逆规划的多智能体概率框架，旨在提升LLMs识别上下文相关评估维度的能力。实验表明，PRISM在多种规模的LLMs上均带来显著改进，尤其在识别最显著评估维度方面表现突出。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly used for emotional support tasks, such as negative thought reframing. This task relies on modifying cognitive appraisals, the subjective interpretation of events that elicit negative emotions, which is typically conceptualized along multiple discrete dimensions. Current LLM-based frameworks model cognitive appraisal by exhaustively evaluating all possible dimensions, but they fail to account for the varying saliency of these dimensions across different contexts. In this work, we investigate a vital yet overlooked question: "Can LLMs infer the salient appraisal dimensions from emotional support conversations?" To address this question, we introduce the AppraiSal benchmark, containing 996 emotional support conversations with human-annotated mental states, including salient cognitive appraisal dimensions. Furthermore, we propose PRISM, a multi-agent probabilistic framework grounded in Bayesian Inverse Planning, designed to improve LLMs' ability to identify context-specific appraisal dimensions. Experimental results show that PRISM brings improvements to LLMs across various sizes, particularly in identifying the most salient appraisal dimensions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。