[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-making-ai-uncertainty-estimates-hold-up-under-data-shift":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},1692,"making-ai-uncertainty-estimates-hold-up-under-data-shift","Making AI Uncertainty Estimates Hold Up Under Data Shift","New research shows that calibrating individual experts in a mixture-of-experts model isn't enough when routing is soft — and proposes a fix.","Researchers have a new method to keep mixture-of-experts models honest about their own uncertainty when the data they see at deployment doesn't match what they trained on.\n\nCalibration, in machine learning, means a model's stated confidence actually reflects how often it's right — if it says 90% confident, it should be correct 90% of the time. Mixture-of-experts (MoE) architectures, which route inputs to specialized sub-models, have shown gains in both accuracy and calibration when each expert is individually calibrated. But a new paper from arXiv finds that guarantee breaks down depending on how routing works. In hard-routed models, where each input goes to exactly one expert, expert-level calibration is sufficient to keep the whole model calibrated even under distribution shift. In soft-routed models, where outputs are a weighted blend of multiple experts, it isn't.\n\nThe distinction matters because soft routing is common in modern large-scale MoE systems, and distribution shift — the gap between training data and real-world deployment conditions — is essentially unavoidable. A model that was well-calibrated in testing but overconfident in production is worse than useless in high-stakes domains like medicine or finance, where the stated probability drives decisions.\n\nTo close the gap, the authors propose adversarial reweighting: a training penalty that explicitly targets calibration errors in the routed aggregate under shifted distributions. They report improvements in the accuracy-calibration tradeoff across model classes and prediction tasks. The caveat, as always with adversarial training methods, is that the hard-distribution scenarios it trains against need to reflect the shifts that actually occur in deployment — a moving target no paper can fully solve.","[\"ai\",\"machine-learning\",\"calibration\",\"mixture-of-experts\"]","2026-06-19T04:00:00.000Z","2026-06-19T10:04:01.674Z","2026-06-19T14:21:37.194Z","published",null,[],"ai",[24,26,27,28],"machine-learning","calibration","mixture-of-experts",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.20544",0,{"sections":35},[36,40,44,49,54,59,64,68,72,77,82,87,92,97],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",491,"2026-06-19T14:59:11.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",132,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",88,"2026-06-16T09:26:09.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Consumer Tech","consumer-tech",78,"2026-06-16T17:58:24.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":58},"Hardware","hardware",62,"2026-06-18T15:24:16.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":63},"Deals","deals",58,"2026-06-19T14:43:50.000Z",{"name":65,"slug":66,"count":62,"latest_published_at":67},"Software","software","2026-06-16T20:00:00.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":18},"Dev Tools","dev-tools",50,{"name":73,"slug":74,"count":75,"latest_published_at":76},"Science","science",38,"2026-06-18T04:00:00.000Z",{"name":78,"slug":79,"count":80,"latest_published_at":81},"Gaming","gaming",31,"2026-06-16T15:25:13.000Z",{"name":83,"slug":84,"count":85,"latest_published_at":86},"General","general",26,"2026-06-13T18:35:15.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"Startups","startups",23,"2026-06-16T15:00:00.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"Reviews","reviews",19,"2026-06-14T08:00:00.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]