[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-neutral-physical-descriptions-still-carry-gender-bias-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},6989,"neutral-physical-descriptions-still-carry-gender-bias-study-finds","Neutral Physical Descriptions Still Carry Gender Bias, Study Finds","Researchers found that gender-neutral physical descriptions still carry strong, measurable gender associations for both human readers and AI language models.","Ditching pronouns for physical descriptions doesn't make text gender-neutral. It just hides the bias in different words.\n\nResearchers built a dataset called GAPA, pairing 316 physical attributes, things like \"short hair\" or \"a defined jawline\", with nearly 15,000 gender-association ratings from 304 US-based annotators. The ratings showed these supposedly neutral descriptions carry consistent, graded gender associations, especially for women and men, with weaker and less consistent patterns for non-binary identities. The team then tested 16 large language models, spanning different families, sizes, and post-training approaches, against those human ratings. The models partly matched human judgments but showed clear quirks: compressed rating scales, weaker alignment on male-coded traits, and a tendency to abstain from rating non-binary associations far more than others.\n\nThe finding undercuts a common recommendation in AI fairness and accessibility circles: swap \"she\" or \"his\" for physical traits to sidestep gendered language. If those substitutes carry their own hidden signals, the swap may just relocate the bias rather than remove it, a real problem for image-captioning tools and any system that treats \"neutral\" description as a solved problem.\n\nThe researchers also released their best proxy model and used it to re-examine character descriptions in the literary dataset LitBank, suggesting this same bias-laundering may already be baked into how literature describes people.","[\"ai\",\"language-models\",\"gender-bias\",\"research\"]","2026-09-18T04:00:00.000Z","2026-09-19T01:57:46.619Z","2026-09-19T01:57:58.548Z","published",null,[],"ai",[24,26,27,28],"language-models","gender-bias","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.16366",0,{"sections":35},[36,39,44,49,54,58,63,68,72,77,82,87,92,97],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",4083,{"name":40,"slug":41,"count":42,"latest_published_at":43},"Security","security",663,"2026-09-18T14:00:14.000Z",{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",339,"2026-09-17T12:00:00.000Z",{"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",155,{"name":59,"slug":60,"count":61,"latest_published_at":62},"Science","science",126,"2026-09-18T14:41:02.000Z",{"name":64,"slug":65,"count":66,"latest_published_at":67},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":18},"Dev Tools","dev-tools",78,{"name":73,"slug":74,"count":75,"latest_published_at":76},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":78,"slug":79,"count":80,"latest_published_at":81},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":83,"slug":84,"count":85,"latest_published_at":86},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"General","general",41,"2026-09-08T01:57:23.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]