Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model
2026-08-10 • Computation and Language
Computation and Language
AI summaryⓘ
The authors developed a new method called FIDM to better understand how people make decisions by looking not just at their actions but also at how much effort they put in, such as hesitations in speech. They used a language model to turn spoken words into detailed records that help separate actions from effort. Testing this on older adults doing a shopping conversation showed the model could accurately identify different decision-related behaviors and helped classify cognitive health better than other methods. This approach adds useful insights beyond traditional ways of analyzing behavior or speech alone.
Inverse decision modelingCognitive tasksResponse dynamicsFactorized inferenceLanguage modelCognitive screeningBehavioral analysisEffort factorTask executionCognitive-status classification
Authors
Jiawen Kang, Dongrui Han, Xixin Wu, Helen Meng
Abstract
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.