Reproduce “TraceMind: Predicting User Information Uptake from Low-Cost Interaction Traces during Human-LLM Content Co-Generation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yu Mei, Fengyou Zu, Ruiwen Zhang, Jie Cai, Chang Liu, Zhoutong Ye, Chun Yu, Yuanchun Shi
TraceMind estimates whether writers can immediately recognize atomic information units in their drafts, not whether they comprehend or remember them. It links each statement across Chat and Draft histories and models spatial, temporal, and workflow interactions. In grouped cross-validation on 1,187 units from 62 participants, it reached 81.17% AUROC versus 76.68% for a full-input early-fusion DNN; this measures recognition, not learning.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.