TraceMind: Predicting User Information Uptake from Low-Cost Interaction Traces during Human-LLM Content Co-Generation

2026-09-11

AI Summary

研究通过低成本交互痕迹预测用户在人机协作生成内容时的信息吸收情况，提出TraceMind模型有效评估信息吸收，超越基线方法。

Abstract

In human-LLM content co-generation, AI-generated information can enter final artifacts without being adequately processed by users, creating risks when artifacts are shared or acted upon. We study whether recognition-level uptake of atomic information units can be assessed in open-ended co-generation and predicted from low-cost interaction traces. We collected data from 62 participants across three tasks. For each final draft, we extracted atomic information units and generated post-task recognition questions, yielding 1187 unit-level uptake labels. We present TraceMind, which tracks units across Chat and Draft histories, aligns interaction traces with changing on-screen layouts, and models spatial, temporal, and workflow-informed evidence. TraceMind outperformed all learned baselines across AUROC, AUPRC-non, balanced accuracy, and macro-F1. We found that uptake unfolds throughout interaction, with sustained active engagement providing informative evidence beyond isolated signals. Our work shifts human-LLM co-generation from content adoption toward what users actually take up, motivating uptake-aware systems grounded in low-cost interaction traces.

Problem

• Human-LLM Content Co-Generation
• User Information Uptake
• Low-Cost Interaction Traces

Innovation

• low-cost interaction traces
• information uptake prediction
• human-LLM co-generation
• spatial-temporal modeling