Sensing What Surveys Miss: Understanding and Personalizing Proactive LLM Support by User Modeling

2026-01-31

AI Summary

This study addresses the decline in user performance during later stages of digital tasks, often caused by high cognitive load or low help-seeking motivation, which hinders timely support. To tackle this challenge, the authors propose a proactive intervention framework that, for the first time, integrates electrodermal activity (EDA) and mouse behavior signals to continuously monitor users’ cognitive states in real time. By combining personalized classifiers with a rule-driven adaptive threshold mechanism, the system dynamically triggers a large language model (LLM) to generate contextually relevant explanations. In an experiment with 32 participants, the approach improved response accuracy by 21%, reduced the false negative rate from 50.9% to 22.9%, and significantly enhanced users’ perceptions of the system’s efficiency, reliability, and benevolence.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Humans and AI: Intelligent User Interfaces
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Difficulty spillover and suboptimal help-seeking challenge the sequential, knowledge-intensive nature of digital tasks. In online surveys, tough questions can drain mental energy and hurt performance on later questions, while users often fail to recognize when they need assistance or may satisfy, lacking motivation to seek help. We developed a proactive, adaptive system using electrodermal activity and mouse movement to predict when respondents need support. Personalized classifiers with a rule-based threshold adaptation trigger timely LLM-based clarifications and explanations. In a within-subjects study (N=32), aligned-adaptive timing was compared to misaligned-adaptive and random-adaptive controls. Aligned-adaptive assistance improved response accuracy by 21%, reduced false negative rates from 50.9% to 22.9%, and improved perceived efficiency, dependability, and benevolence. Properly timed interventions prevent cascades of degraded responses, showing that aligning support with cognitive states improves both the outcomes and the user experience. This enables more effective, personalized LLM-assisted support in survey-based research.

Problem

• help-seeking
• cognitive load
• survey fatigue
• user modeling
• proactive support

Innovation

• user modeling
• proactive LLM support
• electrodermal activity
• adaptive intervention
• cognitive state alignment