[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-judges-favor-their-own-model-family-study-finds":10,"sections":34},{"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":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},6586,"ai-judges-favor-their-own-model-family-study-finds","AI Judges Favor Their Own Model Family, Study Finds","A study of four open-weight model families finds AI judges favor their own kind, and panel makeup alone can flip 18.5% of results.","A new study finds AI models judging other AI models play favorites - literally preferring outputs from their own model family.\n\nResearchers tested four open-weight model families - Llama 3.1, Qwen 2.5, Gemma 2, and Yi 1.5 - in a fully crossed pairwise evaluation totaling 9,312 judgments, the kind of setup increasingly used to grade chatbot outputs without paying humans to do it. A simple per-family scoring method turned out to be nearly indistinguishable from how good a candidate model actually is, correlating with model ability at r = 0.95, so the team built a corrected estimator that holds candidate quality fixed and isolates judge behavior alone. Once quality was controlled for, all four families still showed a same-family bias of 3.4 to 8.4 percentage points, for a global preference score of 0.067 (95% CI 0.053-0.084, p = 0.0002). The bias survived panel-based quality checks, a human-consensus baseline, and a separate replication run in float16 precision.\n\nThat matters because LLM-as-judge panels have quietly become the backbone of many leaderboards and internal eval pipelines that decide which model looks best. This study found that swapping panel composition alone flips 18.5% of pairwise outcomes relative to a family-balanced baseline - meaning who you pick as judges shapes the scoreboard almost as much as the models being judged. A second, compounding issue: simply reordering which answer comes first flips the verdict in 55.4% of AB\u002FBA pairs, far more than random noise should produce.\n\nPut together, this suggests a fair number of published model rankings say as much about judge selection and question order as they do about which model actually wrote the better answer.","[\"ai\",\"llm-as-judge\",\"benchmarking\",\"research\"]","2026-09-17T04:00:00.000Z","2026-09-18T01:23:12.359Z","2026-09-18T01:23:24.267Z","published",null,[],"ai",[24,26,27,28],"llm-as-judge","benchmarking","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.17857",0,{"sections":35},[36,40,44,49,54,58,62,67,72,76,81,86,91,96],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",3853,"2026-09-17T08:27:09.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",648,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",338,"2026-09-11T04:00:00.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":18},"Hardware","hardware",154,{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",114,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":18},"Dev Tools","dev-tools",73,{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",41,"2026-09-08T01:57:23.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]