[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-new-framework-tries-to-rein-in-ai-personality-claims":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},5552,"a-new-framework-tries-to-rein-in-ai-personality-claims","A New Framework Tries to Rein In AI Personality Claims","A new review argues AI psychology research needs the same rigor as human studies, warning that results about AI personalities may be statistical noise.","A new review argues that most AI personality studies are measuring statistical noise, not psychology.\n\nThe paper proposes a dual-validity framework for using large language models in psychological research. It combines psychometric validation, or what a score actually means, with causal inference standards, or what the results can support. The authors argue evidence requirements should scale with the size of the claim: classifying text only needs accuracy and reliability, but claiming a model 'simulates anxiety' or reveals something about cognition needs construct validity evidence and experimental controls. Skip that work, they warn, and researchers risk producing what they call measurement phantoms: regularities in text that look like a psychological signal but aren't tied to anything real inside the model.\n\nThat distinction matters because plenty of recent papers have run LLMs through personality inventories, anxiety scales, and other instruments built for humans, then reported the scores as if the models have inner states comparable to people's. This framework doesn't rule that out. It just says nobody has done the validation work yet to justify the leap from 'the model answered like an anxious person' to 'the model is anxious.'\n\nHuman psychology spent decades building the tools to keep its own measurements honest. Now it's being asked to referee whether a chatbot's quiz answers mean anything at all.","[\"ai\",\"psychology\",\"research-methods\",\"llm-evaluation\"]","2026-08-18T04:00:00.000Z","2026-08-19T01:00:14.982Z","2026-08-19T01:00:27.027Z","published",null,[],"ai",[24,26,27,28],"psychology","research-methods","llm-evaluation",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.16697",0,{"sections":35},[36,40,44,49,54,59,64,69,74,78,83,88,93,98],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",3293,"2026-08-20T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":39},"Security","security",435,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",210,"2026-08-19T09:32:27.000Z",{"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":58},"Hardware","hardware",140,"2026-08-19T18:25:42.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":63},"Consumer Tech","consumer-tech",95,"2026-08-18T16:05:00.000Z",{"name":65,"slug":66,"count":67,"latest_published_at":68},"Science","science",90,"2026-08-19T18:41:02.000Z",{"name":70,"slug":71,"count":72,"latest_published_at":73},"Software","software",73,"2026-08-18T07:51:50.000Z",{"name":75,"slug":76,"count":77,"latest_published_at":18},"Dev Tools","dev-tools",69,{"name":79,"slug":80,"count":81,"latest_published_at":82},"Startups","startups",47,"2026-08-19T19:13:46.000Z",{"name":84,"slug":85,"count":86,"latest_published_at":87},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",33,"2026-08-18T22:18:13.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]