[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-smarter-way-to-teach-llms-to-ask-better-questions":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},3836,"a-smarter-way-to-teach-llms-to-ask-better-questions","A Smarter Way to Teach LLMs to Ask Better Questions","A new fine-tuning method called ASIG helps language models gather information more efficiently, cutting inference costs by 25x on a standard benchmark.","A research team has found a way to make language models dramatically better at asking useful questions in multi-turn conversations.\n\nThe technique, called Amortised Sequential Information Gathering (ASIG), bakes a statistical framework called Bayesian Experimental Design into the model's training rather than applying it at inference time. The team fine-tuned a 7-billion-parameter model using a multi-turn reinforcement learning method with a reward signal based on expected information gain. On the 20 Questions benchmark, ASIG more than doubled the base model's success rate. Inference cost dropped by over 25x compared to BED-LLM, a competing approach that runs the same Bayesian logic at query time instead of baking it into weights.\n\nThe efficiency gap is the real story. Inference-time reasoning methods have become a popular way to squeeze more capability out of existing models, but they carry a compounding cost every time the model takes a turn. Shifting that logic into training means you pay once and redeploy — a trade-off that matters a lot at production scale. The team also tested ASIG on MediQ, a medical diagnosis benchmark the model had never seen, and found the information-seeking behavior transferred, which is harder to fake than benchmark scores on familiar tasks.\n\nThe caveat is that this is a 7B model on controlled benchmarks, not a deployed clinical tool — the gap between \"transfers out of distribution on a benchmark\" and \"works reliably in the wild\" remains as wide as ever.","[\"ai\",\"large-language-models\",\"research\",\"inference\"]","2026-07-07T04:00:00.000Z","2026-07-07T09:41:22.602Z","2026-07-07T09:41:25.533Z","published",null,[],"ai",[24,26,27,28],"large-language-models","research","inference",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.03426",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"]