mlsanityData to 14 Oct 2026

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

arXiv 2608.16394 ↗First posted 17 Aug 2026cs.AI cs.IRcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
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.

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.

Builds on

24 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning12 Jun

Other references · 23

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  4. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  5. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  6. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 267
  7. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  8. 2024RAGGED: Towards Informed Design of Scalable and Stable RAG Systemscited by 24
  9. 2024Multimodal Large Language Model Driven Scenario Testing for Autonomous Vehiclescited by 18
  10. 2024Chat2Scenario: Scenario Extraction From Dataset Through Utilization of Large Language Modelcited by 14
  11. 2024LMM-enhanced Safety-Critical Scenario Generation for Autonomous Driving System Testing From Non-Accident Traffic Videoscited by 9
  12. 2024LeGEND: A Top-Down Approach to Scenario Generation of Autonomous Driving Systems Assisted by Large Language Modelscited by 9
11 more
  1. 2024Adopting RAG for LLM-Aided Future Vehicle Designcited by 6
  2. 2025RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QAcited by 6
  3. 2024Towards Standards-Compliant Assistive Technology Product Specifications via LLMscited by 4
  4. 2024Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Modelscited by 4
  5. 2024NLP-based Regulatory Compliance -- Using GPT 4.0 to Decode Regulatory Documentscited by 4
  6. 2025Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generationcited by 4
  7. 2026TraceLLM: Leveraging Large Language Models with Prompt Engineering for Enhanced Requirements Traceabilitycited by 3
  8. 2025Document Retrieval Augmented Fine-Tuning (DRAFT) for safety-critical software assessmentscited by 2
  9. 2025Classifier or Prompt: A Case Study on Legal Requirements Traceabilitycited by 1
  10. 2025Equipping Retrieval-Augmented Large Language Models with Document Structure Awarenesscited by 1
  11. 2026AI-Driven Test Case Generation from Natural Language Requirements: A Survey of Techniques and Research Gapscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
  2. 2026From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance
  3. 2024Generating Test Scenarios from NL Requirements using Retrieval-Augmented LLMs: An Industrial Study
  4. 2025RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs
  5. 2024LLM-based Unit Test Generation via Property Retrieval
  6. 2025David vs. Goliath: A comparative study of different-sized LLMs for code generation in the domain of automotive scenario generation
  7. 2025Evaluating Retrieval Augmented Generative Models for Document Queries in Transportation Safety
  8. 2025Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive HIL Testing