一作SIGIR 2026Poster· Information Retrieval (Industry)
Bridging Passive and Active: Enhancing Conversation Starter Recommendation via Active Expression Modeling
Yiqing Wu · Haoming Li · Guanyu Jiang · Jiahao Liang · Yongchun Zhu · Jingwu Chen · Feng Zhang
摘要
Large Language Model (LLM)-driven conversational search is shifting information retrieval from reactive keyword matching to proactive, open-ended dialogues. In this context, Conversation Starters are widely deployed to provide personalized query recommendations that help users initiate dialogues....