[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-gasp-detects-which-rag-sentences-are-hallucinated-not-just-whether":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},3925,"gasp-detects-which-rag-sentences-are-hallucinated-not-just-whether","GASP Detects Which RAG Sentences Are Hallucinated, Not Just Whether","A new training-free method scores each sentence in a RAG response by how much its likelihood drops when supporting evidence is removed.","A research paper out this week proposes a way to catch hallucinations in retrieval-augmented generation at the sentence level, not just the answer level.\n\nRetrieval-augmented generation — the approach of feeding a language model relevant documents at query time to ground its answers — reduces fabrication but does not stop it. Most existing detectors return a single score for an entire response, which tells you something went wrong but not where. The new method, called Grounding-Aware Sensitivity by Perturbation (GASP), fixes that by re-scoring each sentence in an answer under three conditions: with full context, with no context, and with each retrieved chunk removed one at a time. A sentence that collapses in likelihood when its source passage disappears is likely grounded; one that barely notices is likely hallucinated.\n\nThe practical upside is that GASP is training-free — it uses a threshold on the grounding features rather than a labeled dataset, which matters a lot for teams that cannot afford to annotate thousands of RAG outputs. Tested on three benchmarks with small instruction-tuned models (under two billion parameters each), it reached a response-level AUC of around 0.73 on RAGTruth and improved on perplexity and self-consistency baselines by clear margins. The one competitive alternative at the span level, a chunk-level entailment verifier, requires a separate model entirely.\n\nThe limits are worth noting: GASP transfers to TofuEval but stumbles on RAGBench's short-answer questions, where models can answer from memorized knowledge rather than retrieved text. That is an honest constraint — grounding sensitivity only works when the answer actually depends on the retrieved context. Most production RAG pipelines do fit that description, but knowledge-heavy Q&A does not.","[\"ai\",\"hallucination\",\"rag\",\"research\"]","2026-07-07T04:00:00.000Z","2026-07-07T12:18:42.463Z","2026-07-07T12:18:45.372Z","published",null,[],"ai",[24,26,27,28],"hallucination","rag","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.04223",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"]