[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-single-word-can-leak-what-a-model-learned":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},7861,"a-single-word-can-leak-what-a-model-learned","A Single Word Can Leak What a Model Learned","Researchers found post-training leaves fingerprints in a model's word choices, letting another model absorb hidden skills from a single word.","Fine-tuning a language model apparently leaves fingerprints on words that have nothing to do with the task you trained it for.\n\nA new arXiv paper introduces a technique called Active Taskless Distillation, or ATD, that transfers a model's post-training gains to a second model using nothing but single-word choices. Researchers picked prompts where a shared \"ancestor\" model was nearly 50\u002F50 on which of two ordinary words to pick next, then trained a fresh copy of that ancestor purely on the small nudges a fine-tuned \"teacher\" version showed in those same word choices. No target-task examples, teacher logits, or access to the teacher's actual parameters were involved. In the main coding experiment, they took a coding-tuned Qwen2.5-1.5B teacher, extracted 5,664 of its single-word prompt responses, and used them alone to train a plain copy of the base model, which then scored 5.34 percentage points higher on the HumanEval+ coding benchmark than a tightly matched control built to strip out that signal while keeping everything else the same.\n\nThis builds on \"subliminal learning\" research that showed a model's traits could bleed into unrelated outputs, but those earlier studies leaned on large amounts of teacher-generated text to pull it off. Here, a single word per prompt is apparently enough, and the effect reportedly also shows up in scientific knowledge, common-sense reasoning, and reading comprehension across different model sizes and families, scaling with how strongly the teacher was originally trained.\n\nIf a single word can smuggle out real capability, anyone trying to audit what a fine-tuned model actually learned, or keep its training data private, has a harder problem than they thought.","[\"ai\",\"ai-research\",\"model-training\",\"ai-safety\"]","2026-09-25T04:00:00.000Z","2026-09-26T03:22:37.011Z","2026-09-26T03:22:42.367Z","published",null,[],"ai",[24,26,27,28],"ai-research","model-training","ai-safety",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.29233",0,{"sections":35},[36,40,45,50,55,60,65,70,75,80,85,90,95,100],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",4570,"2026-09-25T17:16:30.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",741,"2026-09-25T15:52:13.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",390,"2026-09-25T16:24:59.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",256,"2026-09-25T17:00:53.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",185,"2026-09-25T15:00:22.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Science","science",141,"2026-09-25T11:55:23.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Consumer Tech","consumer-tech",132,"2026-09-25T15:30:00.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",88,"2026-09-24T23:06:55.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",82,"2026-09-25T09:59:40.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Startups","startups",76,"2026-09-25T18:33:59.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"General","general",46,"2026-09-25T02:12:57.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"Reviews","reviews",30,"2026-09-24T20:07:31.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]