Chunking German Legal Code
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
Record details
Published: 19 May 2026
Source: arXiv
Category: Research
Topics: Regulation · Finance, VC & PE
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Knowing the Rules Is Not Enough: Student Regulatory Awareness and Use of GenAI in Higher Education
arXiv · 16 May 2026
Quantum Futures Interactive: A Live Demonstration of Post-Quantum Blockchain Security, Infrastructure Tradeoffs, and Sustainable Distributed Trust
arXiv · 15 May 2026
EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA
arXiv · 27 May 2026
Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
arXiv · 10 May 2026
S-SPPO: Semantic-Calibrated Self-Play Preference Optimization
arXiv · 1 June 2026
The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure
arXiv · 4 May 2026
How to cite this record
ethics.ai (19 May 2026), “Chunking German Legal Code,” evidence record 4022, https://ethics.ai/record/4022 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.