TraceMind: Predicting User Information Uptake from Low-Cost Interaction Traces during Human-LLM Content Co-Generation
Yu Mei, Fengyou Zu, Ruiwen Zhang, Jie Cai, Chang Liu, Zhoutong Ye, Chun Yu, Yuanchun Shi
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.
Create a lesson
Related papers
From Review to Reuse: How Post-Task Workflow Can Support Human-AI Agent Interaction
Zekun Wu, Xinru Wang, Rock Yuren Pang et al.
Middleware for Feed Recommendation in Practice: How Feed Creators Build, Maintain, and Sustain Custom Feeds on Bluesky
Tony Zhou, Leijie Wang, Amy X. Zhang
NeuroClick: Preserving Surgeon Autonomy through Hands-Free Earable Tooth-Click Control in Neurosurgery
Jonas Hummel, Maximilian Burzer, Clara Sayffaerth et al.
Understanding Game Coaching on Gig Platforms
Hwijoon Lee, Saiph Savage
Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
Jun Fang, Jiajin Li, Yuntao Wang et al.
When2Talk: When Should a Proactive In-Car Agent Talk?
Kaiser Hamid, Peihang Li, Nade Liang