[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-compact-ai-model-beats-gpt-55-at-rare-disease-diagnosis":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},8693,"compact-ai-model-beats-gpt-55-at-rare-disease-diagnosis","Compact AI Model Beats GPT-5.5 at Rare-Disease Diagnosis","A 9-billion-parameter model trained with a disease knowledge graph edges out GPT-5.5 at ranking rare diagnoses, per an unpublished arXiv preprint.","A 9-billion-parameter AI model just out-diagnosed GPT-5.5 on rare diseases by leaning on a disease knowledge graph instead of brute scale.\n\nThe work, described in an unpublished preprint posted to arXiv (2609.35549), is called RareDx. Its authors built RareDx-Harness, a benchmark that folds messy, incomplete patient records into a single ranked-diagnosis task, then trained the model to reason over phenotypes, genes, and diseases using a shared disease knowledge graph rather than open-ended web retrieval. The training method, RareDx-KGPO, scores answers by how close they land to the correct disease inside that graph and caps the length of a model's guess list, so it cannot rack up partial credit by listing plausible-sounding diagnoses. Across eight benchmarks, the 9-billion-parameter system landed the correct diagnosis in its top 10 guesses 38.34% of the time on average, 1.6 points ahead of GPT-5.5 under the same archived test protocol; a larger 27-billion-parameter version scored 23.53%, 36.56%, and 40.76% at top-1, top-5, and top-10.\n\nThat gap matters because rare-disease diagnosis is exactly where general-purpose chatbots struggle: the conditions are individually rare, sparsely documented, and easy for a model to either miss or fabricate a plausible-but-wrong name for. A relatively compact model beating a frontier system suggests that structure, in this case a curated graph of phenotypes, genes, and diseases, can substitute for raw scale. That is a cheaper, more auditable approach for hospitals or health systems that cannot run frontier-scale infrastructure on every case.\n\nThe paper's own ablations add a useful caveat: bolting on retrieval alone did not reliably help, and the routing and output constraints were what actually drove the gain, not extra data access. That fits a familiar pattern in diagnostic AI, where benchmark leaderboards move years ahead of anything reaching a doctor's screen. RareDx was tested against archived records and rival algorithms, not against a clinician in a real workup, so the real test is whether a graph-grounded model holds up against data messier than any benchmark.","[\"ai\",\"rare-diseases\",\"healthcare-ai\",\"research\"]","2026-09-30T04:00:00.000Z","2026-09-30T19:47:09.123Z","2026-09-30T19:47:15.408Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Attribute the claims to the actual source (this is an unpublished arXiv preprint, arXiv:2609.35549, not a named research team with no citation) and rewrite the final paragraph so it doesn't end on a bare caveat — fold the 'not a clinical trial' point into real closing context or analysis.","resolved","ai",[30,32,33,34],"rare-diseases","healthcare-ai","research",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.35549",0,{"sections":41},[42,45,49,53,58,63,67,72,77,81,86,91,96,101],{"name":43,"slug":30,"count":44,"latest_published_at":18},"AI",5184,{"name":46,"slug":47,"count":48,"latest_published_at":18},"Security","security",791,{"name":50,"slug":51,"count":52,"latest_published_at":18},"Policy","policy",417,{"name":54,"slug":55,"count":56,"latest_published_at":57},"Deals","deals",284,"2026-09-29T21:00:00.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Hardware","hardware",194,"2026-09-29T13:16:04.000Z",{"name":64,"slug":65,"count":66,"latest_published_at":18},"Science","science",155,{"name":68,"slug":69,"count":70,"latest_published_at":71},"Consumer Tech","consumer-tech",142,"2026-09-29T18:38:03.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":76},"Software","software",91,"2026-09-25T20:55:00.000Z",{"name":78,"slug":79,"count":80,"latest_published_at":18},"Dev Tools","dev-tools",90,{"name":82,"slug":83,"count":84,"latest_published_at":85},"Startups","startups",83,"2026-09-29T21:51:36.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",49,"2026-09-28T16:44:57.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]