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

arXiv: https://arxiv.org/abs/2608.16394 · HTML: https://mlsanity.com/paper/2608.16394/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 24 of 24)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [RAGGED: Towards Informed Design of Scalable and Stable RAG Systems](https://mlsanity.com/paper/2403.09040/) (2024)
- [TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning](https://mlsanity.com/paper/2506.10380/) (2025)
- [Multimodal Large Language Model Driven Scenario Testing for Autonomous Vehicles](https://mlsanity.com/paper/2409.06450/) (2024)
- [Chat2Scenario: Scenario Extraction From Dataset Through Utilization of Large Language Model](https://mlsanity.com/paper/2404.16147/) (2024)
- [LMM-enhanced Safety-Critical Scenario Generation for Autonomous Driving System Testing From Non-Accident Traffic Videos](https://mlsanity.com/paper/2406.10857/) (2024)
- [LeGEND: A Top-Down Approach to Scenario Generation of Autonomous Driving Systems Assisted by Large Language Models](https://mlsanity.com/paper/2409.10066/) (2024)
- [Adopting RAG for LLM-Aided Future Vehicle Design](https://mlsanity.com/paper/2411.09590/) (2024)
- [RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA](https://mlsanity.com/paper/2508.09893/) (2025)
- [Towards Standards-Compliant Assistive Technology Product Specifications via LLMs](https://mlsanity.com/paper/2404.03122/) (2024)
- [Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Models](https://mlsanity.com/paper/2408.05933/) (2024)
- [NLP-based Regulatory Compliance -- Using GPT 4.0 to Decode Regulatory Documents](https://mlsanity.com/paper/2412.20602/) (2024)
- [Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation](https://mlsanity.com/paper/2505.19804/) (2025)
- [TraceLLM: Leveraging Large Language Models with Prompt Engineering for Enhanced Requirements Traceability](https://mlsanity.com/paper/2602.01253/) (2026)
- [Document Retrieval Augmented Fine-Tuning (DRAFT) for safety-critical software assessments](https://mlsanity.com/paper/2505.01307/) (2025)
- [Classifier or Prompt: A Case Study on Legal Requirements Traceability](https://mlsanity.com/paper/2502.04916/) (2025)
- [Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness](https://mlsanity.com/paper/2510.04293/) (2025)
- [AI-Driven Test Case Generation from Natural Language Requirements: A Survey of Techniques and Research Gaps](https://mlsanity.com/paper/2606.06563/) (2026)

## Abstract (arXiv)

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.