AI RESEARCH
Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search
arXiv CS.CL
•
ArXi:2605.27066v1 Announce Type: new Understanding how events evolve over time is essential for search engines handling queries about trending news. We present QDET (Query-Driven Event Timeline Summarization), a production system deployed on Baidu Search that constructs focused event timelines to explain specific query events. Unlike traditional topic-centric approaches that aim for comprehensive coverage, QDET identifies and organizes sub-events closely relevant to the query from noisy candidate sets formed by millions of documents retrieved daily.