[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-smarter-way-to-make-llms-forget-harmful-concepts":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},3893,"a-smarter-way-to-make-llms-forget-harmful-concepts","A Smarter Way to Make LLMs Forget Harmful Concepts","MPSelectTune targets the hardest prompts first to strip biased or dangerous concepts from language models more reliably than current methods.","A new fine-tuning method claims to make large language models forget harmful concepts more thoroughly by attacking the problem from its weakest flank.\n\nResearchers introduced MPSelectTune, a two-stage approach to concept unlearning in LLMs. The core insight is that existing methods treat all prompt types equally when trying to scrub a model of unwanted concepts - things like gender bias or knowledge related to bio-weapons. MPSelectTune instead identifies the prompt type where a harmful concept is hardest to remove - the one with the highest concept accuracy - and focuses fine-tuning there. Tested across four benchmarks, it cut worst-case concept accuracy by up to 17% compared to recent baselines while improving main-task accuracy by 2-15%.\n\nThe wider problem here is real: a model that successfully forgets a harmful concept under one phrasing may surface it intact under another. That prompt-sensitivity gap is a known weakness in unlearning research, and it matters because adversarial users will probe exactly those edge cases. A method that explicitly hunts for the hardest prompt and trains against it is a more honest stress test than averaging across all prompt types.\n\nUnlearning is increasingly the fallback plan for AI labs that cannot afford to retrain from scratch every time a safety concern surfaces - so the bar for getting it right keeps rising.","[\"ai\",\"machine learning\",\"llm safety\",\"unlearning\"]","2026-07-07T04:00:00.000Z","2026-07-07T11:04:22.696Z","2026-07-07T11:04:25.598Z","published",null,[],"ai",[24,26,27,28],"machine learning","llm safety","unlearning",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.03932",0,{"sections":35},[36,40,45,50,55,60,65,70,75,79,84,88,93,98],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":18},"Dev Tools","dev-tools",59,{"name":80,"slug":81,"count":82,"latest_published_at":83},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":85,"slug":86,"count":82,"latest_published_at":87},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",29,"2026-07-10T22:28:58.000Z",{"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"]