[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-study-finds-shared-neural-pathways-behind-ai-safety-gaps":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},9240,"study-finds-shared-neural-pathways-behind-ai-safety-gaps","Study Finds Shared Neural Pathways Behind AI Safety Gaps","Researchers found internal pathways that transfer AI safety training across languages, and tuning just those closes gaps in lower-resource languages.","AI chatbots are easier to jailbreak in some languages than others, and a new paper traces why.\n\nResearchers studied how large language models decide to refuse harmful requests, moving past single-neuron analysis to trace multi-layer pathways that carry safety signals through the network. They found each language has its own safety pathway, but also identified a small, shared subset of pathways connecting high-resource languages, like English, to languages with less training data. That overlap functions as an internal bridge, carrying safety behavior learned in high-resource languages over to lower-resource ones. The team then built an alignment method that updates only the parameters inside those shared pathways, instead of fine-tuning the whole model.\n\nMost safety patches either retrain a model broadly or bolt on per-language fixes, both expensive and prone to degrading performance elsewhere. Targeting the shared pathways instead improved refusal rates for harmful requests in lower-resource languages while largely preserving the model's general capabilities, according to the paper.\n\nIt's a mechanistic explanation, not a fix shipped in any product. The usual approach to this problem has been piling on more non-English refusal examples during training - this suggests that was always treating a symptom rather than the cause.","[\"ai safety\",\"llms\",\"multilingual nlp\",\"interpretability\"]","2026-10-01T04:00:00.000Z","2026-10-02T03:31:59.605Z","2026-10-02T03:32:01.065Z","published",null,[],"ai",[26,27,28,29],"ai safety","llms","multilingual nlp","interpretability",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.09095",0,{"sections":36},[37,40,44,48,53,58,62,67,72,76,81,86,91,96],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",5643,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",816,{"name":45,"slug":46,"count":47,"latest_published_at":18},"Policy","policy",430,{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",298,"2026-09-30T21:00:26.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Hardware","hardware",196,"2026-09-30T13:00:00.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",163,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",149,"2026-09-30T22:57:11.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Dev Tools","dev-tools",93,"2026-10-01T02:30:48.000Z",{"name":73,"slug":74,"count":70,"latest_published_at":75},"Software","software","2026-09-30T21:41:11.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",84,"2026-09-30T20:39:09.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",51,"2026-09-30T16:24:30.000Z",{"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",6,"2026-06-16T09:00:00.000Z"]