用思维自述数据提升认知模型发现，让机器更懂人的决策逻辑。
Think-Aloud Reshapes Automated Cognitive Model Discovery Beyond Behavior
- 引入思维自述语言数据约束模型搜索过程
- 在风险决策任务中预测性能显著提升
- 发现模型结构从显式比较转向整合效用，更贴近真实心理机制
以往基于大语言模型的认知模型发现仅依赖行为数据，但此类模型通常存在参数不足问题。本文探索将思维自述（Think Aloud）轨迹作为额外数据约束，用于自动化模型发现。在风险决策领域实验显示，结合思维自述数据所发现的模型，在保留数据上预测性能显著提升。此外，多数参与者（69.4%）的模型结构发生根本性变化，由显式比较类转向整合效用类。结果表明，过程级语言数据不仅能提高模型拟合度，还能系统性重塑认知模型结构，揭示出仅从行为数据无法识别的心理机制。
原文摘要 · Abstract (English)
Computational cognitive models discovered using large language models have so far relied solely on behavioral data. However, it is well-known that models produced from the behavioral trajectory alone are typically under-determined. In this work, we explore the use of Think Aloud traces as an additional form of data constraint during automated model discovery. When applied to the domain of risky decision-making, we find that the models discovered with think-aloud achieve significantly improved predictive performance on held-out data. Additionally, we find that the discovered models belong to different structural classes than those discovered from behavior alone for the majority of participants (69.4\%), specifically, it shifts from Explicit comparator towards Integrated utility. These results suggest that process-level language data not only improve model fit, but also systematically reshape the structure of the discovered cognitive models, enabling the identification of mechanisms that are not recoverable from behavior alone.
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。