ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling
Published in arXiv (Cornell University) • Dec 24, 2025
Authors:,,
Chuan Wang
Gaoming Yang
Han Wu
Abstract
Industrial recommender systems face two fundamental limitations under the log-driven paradigm: (1) knowledge poverty in ID-based item representations that causes brittle interest modeling under data sparsity, and (2) systemic blindness to beyond-log user interests that constrains model performance w...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!