用对话模式预测人的决策风格，准确率达AUC 0.8
Capturing Human Cognitive Styles with Language: Towards an Experimental Evaluation Paradigm
- 通过实验设计测量人类决策行为，构建语言与认知风格的对应关系
- 语言特征可中高精度预测个体决策风格（AUC ~ 0.8）
- 为语言模型评估认知状态提供可复现的实验范式，适合认知计算研究者
尽管自然语言处理模型常通过语言来捕捉认知状态，但其有效性通常依赖于无法获取作者认知状态的标注。在行为科学中，认知状态则通过实验进行测量。本文提出一种基于实验的评估框架，用于检验基于语言的认知风格模型与人类行为的一致性。研究聚焦于决策过程及其与个体谈论近期决策时语言风格的关系。参与者先完成一项经典决策实验，以捕捉其认知风格——即决策过程中偏好变化的方式。结果表明，旨在反映认知风格的语言特征，能以中高精度（AUC ~ 0.8）预测个体的决策风格，证明了认知风格可通过话语模式部分揭示。
原文摘要 · Abstract (English)
While NLP models often seek to capture cognitive states via language, the validity of predicted states is determined by comparing them to annotations created without access the cognitive states of the authors. In behavioral sciences, cognitive states are instead measured via experiments. Here, we introduce an experiment-based framework for evaluating language-based cognitive style models against human behavior. We explore the phenomenon of decision making, and its relationship to the linguistic style of an individual talking about a recent decision they made. The participants then follow a classical decision-making experiment that captures their cognitive style, determined by how preferences change during a decision exercise. We find that language features, intended to capture cognitive style, can predict participants' decision style with moderate-to-high accuracy (AUC ~ 0.8), demonstrating that cognitive style can be partly captured and revealed by discourse patterns.
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。