用语言模型分解认知决策，提升老年人认知筛查精度。
Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model
- 将决策过程拆分为行动与努力两个独立因子，分别建模个体差异。
- 在400名老人的购物对话数据中，准确分离出行为偏差与执行难度。
- 比传统方法更适配临床认知评估，尤其擅长发现细微行为异常。
逆决策建模通过观测行为推断决策内在属性，但现有方法主要依赖动作轨迹。在言语化认知任务中，除动作外，还存在语言生成、交互和停顿等未被建模的反应动态。本文提出因子化逆决策模型（FIDM），将个体任务执行概率分解为行动因子与努力因子，由各自独立的个体参数控制。基于原始口语转录文本，语言模型生成结构化任务执行轨迹以支持因子化推断。在400名老年人完成购物对话认知筛查的数据上，受控恢复实验显示能选择性估计预期因子；匹配半合成条件下，即便整体行为汇总一致，FIDM仍保持行动与执行难度的区分能力。动作证据进一步定位了参与者间任务定义的偏离。在认知状态分类中，FIDM提供的信息与临床评分、轨迹摘要及静态语言表征互补，在二分类设置下对所有基线均实现持续提升。
原文摘要 · Abstract (English)
Inverse decision modeling infers latent properties of decision processes from observed behavior, but existing formulations rely primarily on action trajectories. In verbalized cognitive tasks, task execution also produces response dynamics that action-only formulations leave unmodeled, such as verbal production, interaction, and hesitation. We propose a factorized inverse decision model (FIDM) that decomposes each individual's task-execution likelihood into an action factor and an effort factor, governed by separate individual-specific parameters. From raw verbal transcripts, a language model produces structured task-execution traces for factorized inference. On data from 400 older adults performing a grocery-shopping dialog task for cognitive screening, controlled recovery shows selective estimation of the intended factors, while matched semi-synthetic conditions show that FIDM preserves action-execution distinctions even when aggregate behavioral summaries are matched. Action evidence further localizes task-defined deviations across participants. In cognitive-status classification, FIDM provides information complementary to clinical scores, trajectory summaries, and frozen language representations, with consistent gains across all evaluated baselines in the binary setting.
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。