{"paper":{"title":"LegalCheck: Retrieval- and Context-Augmented Generation for Drafting Municipal Legal Advice Letters","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"A retrieval- and context-augmented system generates near-final municipal legal advice letters in minutes rather than hours.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Julien Rossi, Virgill van der Meer","submitted_at":"2026-05-12T12:01:29Z","abstract_excerpt":"Public-sector legal departments in the Netherlands face acute staff shortages, increased case volumes, and increased pressure to meet regulatory compliance. This paper presents LegalCheck, a novel system that addresses these challenges by automating the drafting of objection response letters through a combination of Retrieval-Augmented Generation (RAG) and Context-Augmented Generation (CAG). Using a large language model (LLM) alongside curated legal knowledge bases, LegalCheck performs retrieval of relevant laws and precedents, and uses controlled prompting to incorporate both external knowled"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In a real-world deployment within the Municipality of Amsterdam, LegalCheck produced near-final advice letters in minutes rather than hours, while maintaining high legal consistency and factual accuracy. The output captured the vast majority of required legal reasoning (often 80% to 100% of essential content).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That expert-in-the-loop review combined with retrieval from curated legal knowledge bases is sufficient to prevent legally significant errors or omissions in the generated drafts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LegalCheck applies RAG and CAG to generate draft legal advice letters from laws and precedents, achieving 80-100% coverage of essential reasoning in minutes during a municipal deployment.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A retrieval- and context-augmented system generates near-final municipal legal advice letters in minutes rather than hours.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bd8b9e30f7d5e61b7392846ed11b9239a746bd5d909375d84dde2c3c0d936e7e"},"source":{"id":"2605.12012","kind":"arxiv","version":2},"verdict":{"id":"8cc99ec5-8267-4b02-9aad-fba064200e51","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T04:58:09.276141Z","strongest_claim":"In a real-world deployment within the Municipality of Amsterdam, LegalCheck produced near-final advice letters in minutes rather than hours, while maintaining high legal consistency and factual accuracy. The output captured the vast majority of required legal reasoning (often 80% to 100% of essential content).","one_line_summary":"LegalCheck applies RAG and CAG to generate draft legal advice letters from laws and precedents, achieving 80-100% coverage of essential reasoning in minutes during a municipal deployment.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That expert-in-the-loop review combined with retrieval from curated legal knowledge bases is sufficient to prevent legally significant errors or omissions in the generated drafts.","pith_extraction_headline":"A retrieval- and context-augmented system generates near-final municipal legal advice letters in minutes rather than hours."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.12012/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T11:34:25.608111Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T09:01:16.846798Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T07:58:49.681538Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ede4ed643949e5e8731c36a40a165fbab2c8c6266c362eb229488714da636e7f"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}