[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-splitting-ai-review-into-two-passes-curbs-dropped-content":10,"sections":40},{"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":30,"tags":31,"sources":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},6648,"splitting-ai-review-into-two-passes-curbs-dropped-content","Splitting AI Review Into Two Passes Curbs Dropped Content","Splitting AI review into two passes cuts dropped content by roughly a third, but researchers call it a mitigation, not a cure, since two failure modes remain.","Ask a multimodal AI model to review a long recording or document in one shot, and it will quietly skip about a third of it.\n\nNew research tests what happens when a multimodal model reviews long sources in a single pass versus two. The one-pass approach drops roughly a third of the content and pads the rest with embellishment, and it is not a perception problem: the same dropped material reappears when the model is simply asked to transcribe the source. The bottleneck is capacity: one pass can't perceive, reason, and write a faithful long review at the same time, and even a much larger reasoning budget doesn't help, because the model spends it planning a review instead of transcribing the source. Splitting the job into two passes with the same model weights, first transcribing then reviewing the transcript, improved both faithfulness and coverage across a 21-source test suite.\n\nThis is a structural fix for a problem you can't prompt your way out of, since more reasoning time just makes the model plan a review of content it hasn't written down yet. It matters for anyone using AI to summarize meetings, contracts, or scanned documents, where losing a third of the material is the difference between a useful summary and a liability. It also suggests the industry's habit of throwing bigger reasoning budgets at problems is solving the wrong one here.\n\nStill, the researchers call this a mitigation, not a cure: the review pass can run out of room on very long sources, and once the transcript is out of context, the model can start confabulating from memory anyway.","[\"ai\",\"llm-research\",\"multimodal-ai\",\"ai-evaluation\"]","2026-09-17T04:00:00.000Z","2026-09-18T04:18:33.747Z","2026-09-18T04:18:45.643Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"The dek claims the two-pass approach 'fixes' the dropped-content problem, but the body explicitly calls it 'a mitigation, not a cure' and lists two failure modes that persist — rewrite the dek to match that qualified framing.","resolved","ai",[30,32,33,34],"llm-research","multimodal-ai","ai-evaluation",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.18958",0,{"sections":41},[42,46,50,55,60,64,68,73,78,82,87,92,97,102],{"name":43,"slug":30,"count":44,"latest_published_at":45},"AI",3853,"2026-09-17T08:27:09.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":18},"Security","security",648,{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",338,"2026-09-11T04:00:00.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":18},"Hardware","hardware",154,{"name":65,"slug":66,"count":67,"latest_published_at":18},"Science","science",114,{"name":69,"slug":70,"count":71,"latest_published_at":72},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":74,"slug":75,"count":76,"latest_published_at":77},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":18},"Dev Tools","dev-tools",73,{"name":83,"slug":84,"count":85,"latest_published_at":86},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"General","general",41,"2026-09-08T01:57:23.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":103,"slug":104,"count":105,"latest_published_at":106},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]