Metraipolis › archive › dc_d61eb68cdd5f

Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152 — arXiv:2608.16394

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16394
License (as archived)
CC0-1.0
Archived
2026-10-18T17:44:36.173Z
SHA-256 of the archived text
93ba8bcb05d2ffffaed2234e051a982d4e5ad337a680f3b114796d970e316966
Stable URL of this page
https://metraipolis.com/documento/dc_d61eb68cdd5f

How to cite

Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152 — arXiv:2608.16394 — arXiv (en), https://arxiv.org/abs/2608.16394 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d61eb68cdd5f (Metraipolis archive dc_d61eb68cdd5f, sha256 93ba8bcb05d2ffffaed2234e051a982d4e5ad337a680f3b114796d970e316966)
BibTeX
@misc{dcd61eb68cdd5f,
  title = {Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152 — arXiv:2608.16394},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16394},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d61eb68cdd5f; sha256 93ba8bcb05d2ffffaed2234e051a982d4e5ad337a680f3b114796d970e316966},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16394. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generating regulation-compliant test scenarios is essential for validating safety-critical automotive systems, yet Large Language Models (LLMs) struggle to ground outputs in long, hierarchical standards. We present RegulaRAG, a Retrieval-Augmented Generation (RAG) pipeline that couples SmartChunking, reference-aware enrichment of paragraphs and tables via graph traversal, with Smart Retrieve & Rerank over these enriched units. To test our system, we evaluate on a manually curated dataset covering all scenarios in UN Regulation No. 152 (AEBS). Our study comprises: (i) a three-step progressive search that identifies near-optimal retrieval parameters without exhaustive grid search; (ii) head-to-head comparisons against five baseline RAG systems; and (iii) a robustness stress test that scales the source corpus with distractor content. Outputs are evaluated using a customized penalized scoring metric. Across all experiments, RegulaRAG achieves the highest average Meta-Score (82.99), outperforming the next-best system by 43% (NoRAG: 57.94), while operating at 14k-25k tokens per query versus up to 500k for graphcentric baselines. It maintains strong performance, remaining stable even as the number of regulatory sources grows, whereas competing RAG systems degrade sharply in both quality and robustness.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.16394 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.866Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).