[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-qwen3-reasons-fine-in-english-falls-apart-in-other-languages":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},8618,"qwen3-reasons-fine-in-english-falls-apart-in-other-languages","Qwen3 Reasons Fine in English, Falls Apart in Other Languages","A study of Qwen3 reasoning models finds non-English users get complete answers 15-18% of the time versus 93% for English, until RL rewards language too.","Qwen3 can solve competition math problems in any language. It just won't show its work outside English.\n\nResearchers audited thirteen endpoints across the Qwen3 model family on competition-mathematics problems in eleven languages, checking whether each attempt actually finished with a correct, visible chain of reasoning in the language the user asked in. In English, 92.9% of problems got a complete, correct solution. In the ten other languages, that number dropped to 15.4-17.9%, even across sixteen attempts per problem. Multilingual supervised fine-tuning brought reasoning back into the target language, but it also lowered accuracy and made non-English reasoning traces more prone to looping forever without finishing. Reinforcement learning fixed that non-termination problem across the board, but only the version whose reward function explicitly scored language match kept answers in the requested language - rewarding correctness alone just pulled the model back into English.\n\nThis isn't a benchmark curiosity. A model that can solve a problem but only delivers the answer in English isn't giving non-English speakers a weaker experience - it's giving them no access to the same capability. That distinction matters for anyone deploying open reasoning models outside English-speaking markets, and it points to reward design, not training-data volume, as the lever that actually closes the gap.\n\nThe fix here isn't \"add more languages to the pretraining mix\" - it's \"tell the reward function to care,\" a cheaper and more surgical move than the field's usual instinct to just scale up multilingual data.","[\"ai\",\"multilingual-ai\",\"reasoning-models\",\"reinforcement-learning\"]","2026-09-30T04:00:00.000Z","2026-09-30T15:16:57.643Z","2026-09-30T15:17:03.476Z","published",null,[],"ai",[24,26,27,28],"multilingual-ai","reasoning-models","reinforcement-learning",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.37104",0,{"sections":35},[36,39,43,47,52,57,62,67,72,76,81,86,91,96],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",5135,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",788,{"name":44,"slug":45,"count":46,"latest_published_at":18},"Policy","policy",417,{"name":48,"slug":49,"count":50,"latest_published_at":51},"Deals","deals",284,"2026-09-29T21:00:00.000Z",{"name":53,"slug":54,"count":55,"latest_published_at":56},"Hardware","hardware",194,"2026-09-29T13:16:04.000Z",{"name":58,"slug":59,"count":60,"latest_published_at":61},"Science","science",154,"2026-09-28T13:19:18.000Z",{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",142,"2026-09-29T18:38:03.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Software","software",91,"2026-09-25T20:55:00.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":18},"Dev Tools","dev-tools",90,{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",83,"2026-09-29T21:51:36.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"General","general",49,"2026-09-28T16:44:57.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"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"]