[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-study-finds-fine-tuning-cuts-bias-in-ai-triage-tools":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},9565,"study-finds-fine-tuning-cuts-bias-in-ai-triage-tools","Study Finds Fine-Tuning Cuts Bias in AI Triage Tools","An audit of ten open-source AI models finds bias in pediatric ER triage predictions doesn't track with model size or medical-specific training.","Fine-tuning a small open-source language model made it less likely to change its emergency-room triage call based on a patient's race, income, or insurance status than the bigger, fancier version it was built on.\n\nResearchers audited ten open-source LLMs on pediatric Emergency Severity Index predictions, including Qwen2.5-7B, Qwen2.5-14B-Instruct, a QLoRA fine-tuned Qwen2.5-7B, MedGemma variants, MedLLaMA2-7B, and GPT-OSS-20B and 120B. They fed each model near-identical clinical vignettes that differed in only one injected detail, things like a child's socioeconomic background, housing status, or how they arrived at the hospital, and tracked how often the triage level changed anyway. The fine-tuned Qwen2.5-7B shifted its answer in just 5.27% of these counterfactual pairs, versus 16.02% for the base Qwen2.5-7B it was tuned from, with a correspondingly smaller mean absolute shift (0.0534 versus 0.1706). Several larger models and medical-domain-pretrained models, the ones you'd expect to do better, showed bigger shifts instead.\n\nThat non-relationship between size, medical training, and fairness is the real finding here. It suggests hospitals treating \"the biggest model\" or \"the one trained on medical data\" as a built-in bias safeguard are checking the wrong box; sensitivity to irrelevant patient details has to be measured directly, not assumed from a spec sheet. The study's stratified analysis also found consistent directional patterns in who gets over- or under-triaged, not just random noise.\n\nCheap, lightweight counterfactual audits like this one could become a standard pre-deployment checklist item, much like bias testing became routine for hiring algorithms, except a missed bias here gets measured in ESI levels, not rejected resumes.","[\"ai bias\",\"clinical ai\",\"open-source llms\",\"healthcare\"]","2026-10-02T04:00:00.000Z","2026-10-03T00:49:58.638Z","2026-10-03T00:50:05.116Z","published",null,[],"ai",[26,27,28,29],"ai bias","clinical ai","open-source llms","healthcare",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.01963",0,{"sections":36},[37,40,44,48,53,57,61,66,71,76,81,86,91,96],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",5896,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",837,{"name":45,"slug":46,"count":47,"latest_published_at":18},"Policy","policy",438,{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",317,"2026-10-01T22:00:00.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":18},"Hardware","hardware",199,{"name":58,"slug":59,"count":60,"latest_published_at":18},"Science","science",171,{"name":62,"slug":63,"count":64,"latest_published_at":65},"Consumer Tech","consumer-tech",155,"2026-10-01T19:54:10.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Dev Tools","dev-tools",96,"2026-10-01T16:57:03.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Software","software",93,"2026-09-30T21:41:11.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",90,"2026-10-01T21:55:22.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]