Adapting general-purpose large language models to specific tasks requires substantial human effort in designing data and training strategies. Sustaining improvement is especially challenging because model updates change the error distribution, requiring strategies to be continually refined. We introduce ImproveAnyTask,...
Xing-Bo Yao, Xiao-Man Wang, Zheng-Wu Lei et al.· 0 citations
This paper designs TACT to revise student-generated actions, test the revisions through partner responses, and distill useful feedback into the student, which helps improve social goal attainment while reducing communication cost.
Lin-Xiao Gong, Yijie Xu, Tian-Fu Wang et al.· 0 citations
TSN4PI, a unified framework for tracking the evolution of political ideologies on social media, includes two core modules: the PIDN and the PIPN, which employs temporal graph neural networks to predict future ideological shifts, enabling comprehensive analysis of ideology presence, intensity, and evolution.