[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-benchmark-finds-ai-struggles-with-long-document-structure":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},5157,"new-benchmark-finds-ai-struggles-with-long-document-structure","New Benchmark Finds AI Struggles With Long Document Structure","LongDocBench finds AI document parsers ace single pages but struggle to rebuild tables of contents and figure-caption links in long documents.","A new benchmark says today's AI document parsers can read a single page just fine, but they get lost trying to map out the document around it.\n\nResearchers built LongDocBench from 85 real-world financial reports, textbooks, and academic papers totaling 2,582 pages, with some documents running up to 105 pages. It tests two things most document-parsing benchmarks skip: rebuilding a document's full table-of-contents hierarchy across pages, and tracing the links between tables or figures and their captions, notes, and sources. The dataset includes 3,937 human-verified heading nodes with an average nesting depth of 3.55 (max depth 9) and 3,258 contextual relationships tied to 2,680 table and figure objects. When the researchers fed human-verified TOC structures and relationship data into long-document question-answering tests, reasoning accuracy improved, and combining both types of structure helped more than either alone.\n\nMost document-AI benchmarks measure whether a parser can read one page correctly - text order, tables, formulas. LongDocBench targets the layer above that: whether a system understands how a hundred-page report is actually organized, which matters for anyone building tools to summarize or query long filings, textbooks, or papers. The paper's own tests found current parsers handle page-level recognition well but still fall short on both structure-recovery tasks.\n\nThat gap suggests the polished demos of AI reading long PDFs are running ahead of the underlying plumbing.","[\"document-ai\",\"benchmarks\",\"llm-evaluation\",\"research\"]","2026-08-18T04:00:00.000Z","2026-08-18T07:30:03.973Z","2026-08-18T07:30:15.773Z","published",null,[],"ai",[26,27,28,29],"document-ai","benchmarks","llm-evaluation","research",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.15064",0,{"sections":36},[37,41,45,50,55,60,65,70,75,79,84,89,94,99],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",3293,"2026-08-20T04:00:00.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":40},"Security","security",435,{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",210,"2026-08-19T09:32:27.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",140,"2026-08-19T18:25:42.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",95,"2026-08-18T16:05:00.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Science","science",90,"2026-08-19T18:41:02.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",73,"2026-08-18T07:51:50.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":18},"Dev Tools","dev-tools",69,{"name":80,"slug":81,"count":82,"latest_published_at":83},"Startups","startups",47,"2026-08-19T19:13:46.000Z",{"name":85,"slug":86,"count":87,"latest_published_at":88},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",33,"2026-08-18T22:18:13.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]