Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration

2026-09-09

AI Summary

本文针对小样本移动感知研究中准确预测难及模型解释性不足的问题，提出了一种由大语言模型指导的概念集成变换器（CIT）方法。

Abstract

Mobile sensing enables longitudinal monitoring of behavioral and physiological patterns in everyday settings. However, accurate prediction remains challenging in small-cohort health-sensing studies, where task-specific outcome supervision is limited relative to heterogeneous sensing data. Interpretability is also important, as model outputs should reflect meaningful behavioral and physiological patterns rather than predictive scores alone. We develop a Concept-Integrated Transformer (CIT) with LLM-guided concept supervision for explainable prediction from mobile sensing data. CIT uses a pretrained large language model to generate baseline-aware concept abnormality targets with confidence weights without manual concept annotation. Across two longitudinal datasets, CIT achieves the highest F1 score on AFFECT (0.756) and ties for the highest on a PHQ-9 dataset (0.765). The learned concept scores also reveal interpretable behavioral and physiological patterns; in AFFECT, sleep quantity and quality show the clearest difference between high and low negative affect groups. These findings support LLM-guided concept integration for accurate and interpretable prediction in small-cohort mobile sensing studies.

Problem

• mobile sensing
• small-cohort studies
• interpretability
• predictive accuracy

Innovation

• Concept-Integrated Transformer (CIT)
• LLM-guided concept supervision
• mobile sensing data
• explainable prediction
• behavioral and physiological patterns