{
  "id": 4022,
  "url": "https://arxiv.org/abs/2605.19806v2",
  "title": "Chunking German Legal Code",
  "summary": "This paper investigates chunking strategies for retrieval-augmented generation on German statutory law, using the German Civil Code as a structured benchmark corpus. We implement and compare a range of segmentation approaches, including structural units (sections, subsections, sentences, propositions), fixed-size windows, contextual chunking, semantic clustering, Lumber-style chunking, and RAPTOR-based hierarchical retrieval. All methods are evaluated on a legal question-answering dataset with s",
  "authors": "Max Prior, Natalia Milanova, Andreas Schultz",
  "category": "research",
  "topics": "regulation,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-19T13:04:58.000Z",
  "fetched_at": "2026-07-14T16:30:41.582Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4022",
  "original_url": "https://arxiv.org/abs/2605.19806v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}