[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86160-en":3,"doc-seo-86160-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86160,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Query-Focused Event Summarization: A Dataset and Benchmark","Query-focused event summarization builds summaries for a thematic event that match user queries spanning different aspects of the same real-world phenomenon. Existing query-focused summarization datasets and methods lack event-level designs and often degrade on large-scale thematic corpora. QFES (Query-Focused Event Summarization) introduces the task and a benchmark dataset QFESum with 8 events, 16,684 documents, and 104 queries, plus a two-stage framework combining query-focused retrieval and hierarchical-clustering summarization. Experiments validate improved event-granularity performance.","arXiv :2607 . 1 1 166v 1 [ cs .CL] 13 Jul 2026  \nQUERY-FOCUSED EVENT SUMMARIZATION: A DATASET AND BENCHMARK  \nCHENYU HU AND BANG WANG*  \nABSTRACT. Thematic corpus refers to a corpus of semantically coherent documents that collectively describe different aspects of a shared thematic event. Thematic corpus typically contains hundreds or even thousands of documents. While users’ concerns on the thematic event often span multiple dimensions, QueryFocused Summarization (QFS) aims to generate summaries tailored to users’ queries. However, existing QFS datasets lack event summarization, and most QFS methods struggle with large-scale datasets. To address these challenges, we propose QFES (Query-Focused Event Summarization) task and construct QFESum dataset, which contains 8 thematic events, 16,684 documents, and 104 queries. Furthermore, we introduce a two-stage QFES framework consists of Query-Focused Retrieval with Adaptive Thresholding (RAT) and Query-Focused Summarization based on Hierarchical Clustering (SHC) . Experimental results on QFESum show that RAT and SHC perform consistently better than baselines, demonstrating their effectiveness in QFES. The dataset and code are publicly available at [https://github.com/sarcasm-hcy02/](https://github.com/sarcasm-hcy02/)[ ](https://github.com/sarcasm-hcy02/)QFES-QFESum.  \n1. INTRODUCTION  \nA thematic corpus refers to a collection of semantically coherent documents or reports that collectively describe different aspects of a shared thematic event. Thematic events such as “global financial crisis”span multiple dimensions including economy, society, and politics, and involve massive heterogeneous thematic corpus. Fully understanding such thematic events requires substantial human effort, making automatic summarization highly valuable in real-world thematic events analysis. As a result, summarization techniques have been widely explored: Multi-Documents Event Summarization(MDES) [31] aims to generate a coherent and concise event summary that captures the main content from documents. However, MDES produces only a generic summary for the entire thematic corpus, whereas different users often have distinct interests. For a given thematic event, different people may focus on different aspects: environmental organizations emphasize ecological impacts, investors pay attention to financial risks, while policymakers are concerned with regulatory responsibilities.  \nTherefore, Query-Focused Summarization (QFS) has been proposed to generate summaries tailored to users’ distinct queries. However, existing QFS datasets and methods lack designs specifically tailored to events, while event summarization is one of the most widely demanded and frequently used summarization scenarios. Thus we propose Query-Focused Event Summarization task (QFES), which aims to generate event summaries focused on users’ query from a thematic corpus.  \nCompared with QFS, QFES differs substantially in terms of datasets, algorithms, and evaluation. At the dataset level, a QFES dataset requires thematic corpus, together with corresponding queries, where each query represents a specific aspect of the thematic event. Moreover, each document in the corpus should be associated with query labels indicating which aspects the document is related to. Atthe algorithmic level, a QFES method is expected to first retrieve documents relevant to a given query from the thematic corpus, and then generate a summary whose content is focused on the query-specified aspect of the thematic event. At the evaluation level, in addition to conventional word-level metrics such  \nDate: July 14, 2026 .  \n*Corresponding author.  \n2 CHENYU HU AND BANG WANG  \nas ROUGE, QFES summaries should be assessed crucially from an event-granularity perspective. That means evaluation should examine whether the events in the generated summary can be properly semantic matched with those in the reference summary.  \nDespite existing progress in QFS and MDES research, several l","cbCaikApgpHtisCf","https://ap.wps.com/l/cbCaikApgpHtisCf","pdf",1227977,3,1,22,"English","en",105,"# Introduction\n## Related Work and Limitations\n## Proposed Task and Dataset Construction\n## Two-Stage Framework","[{\"question\":\"What problem does Query-Focused Event Summarization (QFES) address?\",\"answer\":\"QFES generates event summaries tailored to a user’s query aspect within a thematic corpus, rather than producing one generic summary for the entire event.\"},{\"question\":\"What is included in the QFESum dataset?\",\"answer\":\"QFESum contains 8 thematic events, 16,684 documents, and 104 queries, with document-level relevance annotations and query-focused reference summaries.\"},{\"question\":\"How does the proposed two-stage QFES framework work?\",\"answer\":\"It first retrieves query-relevant documents using Query-Focused Retrieval with Adaptive Thresholding (RAT), then generates query-focused summaries using Query-Focused Summarization based on Hierarchical Clustering (SHC).\"}]",1784208993,55,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"query-focused-event-summarization-a-dataset-and-benchmark","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/query-focused-event-summarization-a-dataset-and-benchmark/86160/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Query-Focused Event Summarization (QFES) address?","Question",{"text":75,"@type":76},"QFES generates event summaries tailored to a user’s query aspect within a thematic corpus, rather than producing one generic summary for the entire event.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is included in the QFESum dataset?",{"text":80,"@type":76},"QFESum contains 8 thematic events, 16,684 documents, and 104 queries, with document-level relevance annotations and query-focused reference summaries.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed two-stage QFES framework work?",{"text":84,"@type":76},"It first retrieves query-relevant documents using Query-Focused Retrieval with Adaptive Thresholding (RAT), then generates query-focused summaries using Query-Focused Summarization based on Hierarchical Clustering (SHC).","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]