[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-pipeline-strips-legal-reasoning-from-330000-italian-tax-rulings":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},3826,"ai-pipeline-strips-legal-reasoning-from-330000-italian-tax-rulings","AI Pipeline Strips Legal Reasoning From 330,000 Italian Tax Rulings","Researchers built an automated system to parse Italian tax-court decisions into structured legal arguments, with a filter to catch fabricated citations.","An AI pipeline can now break down Italian tax-court judgments into structured legal arguments at scale — and flag when the model makes up case citations.\n\nResearchers built a system that ingests roughly 330,000 first- and second-instance Italian tax-court decisions and decomposes each one into individual legal issues. For every issue, the pipeline produces an XML representation organized around the IRAC framework — Issue, Rule, Application, Conclusion — and the classical legal syllogism. The team chose DeepSeek V3 as the underlying model, citing the need to process hundreds of thousands of documents without blowing the budget. A dedicated citation parser called Linkoln checks the model's references against identifiers actually found in each judgment, catching hallucinated case law before it contaminates downstream analysis.\n\nLegal AI has a well-known citation problem: models confidently produce plausible-sounding but nonexistent case references, a failure mode that has embarrassed lawyers in live court filings. Grounding the model's output against a structured parser and standard identifiers — URN-NIR, ECLI, CELEX — is a more systematic answer to that problem than prompting alone. The researchers validated against 50 judgments annotated by two tax-law PhDs, measuring both inter-annotator agreement and how closely the model matched expert analysis.\n\nThe authors call it the first expert-validated, issue-level extraction pipeline with hallucination control for Italian tax courts, which is a narrow enough claim to be credible. Whether the approach scales to other legal systems with messier citation norms is the question worth asking next.","[\"ai\",\"legal-tech\",\"llm\",\"research\"]","2026-07-07T04:00:00.000Z","2026-07-07T09:27:36.233Z","2026-07-07T09:27:39.269Z","published",null,[],"ai",[24,26,27,28],"legal-tech","llm","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.03325",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"]