AI RESEARCH
Quality Over Clicks: Intrinsic Quality-Driven Iterative Reinforcement Learning for Cold-Start E-Commerce Query Suggestion
arXiv CS.CL
•
ArXi:2603.22922v1 Announce Type: new Existing dialogue systems rely on Query Suggestion (QS) to enhance user engagement. Recent efforts typically employ large language models with Click-Through Rate (CTR) model, yet fail in cold-start scenarios due to their heavy reliance on abundant online click data for effective CTR model