# Explicating Tacit Regulatory Knowledge from LLMs to Auto-Formalize Requirements for Compliance Test Case Generation

arXiv: https://arxiv.org/abs/2601.09762 · HTML: https://mlsanity.com/paper/2601.09762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 52 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 8 of 8)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Unit Test Case Generation with Transformers and Focal Context](https://mlsanity.com/paper/2009.05617/) (2020)
- [LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs](https://mlsanity.com/paper/2404.10304/) (2024)
- [Flakify: A Black-Box, Language Model-based Predictor for Flaky Tests](https://mlsanity.com/paper/2112.12331/) (2021)
- [Automatic High-Level Test Case Generation using Large Language Models](https://mlsanity.com/paper/2503.17998/) (2025)
- [Generating High-Level Test Cases from Requirements using LLM: An Industry Study](https://mlsanity.com/paper/2510.03641/) (2025)
- [GenAI-based test case generation and execution in SDV platform](https://mlsanity.com/paper/2509.05112/) (2025)
- [LLMCFG-TGen: Using LLM-Generated Control Flow Graphs to Automatically Create Test Cases from Use Cases](https://mlsanity.com/paper/2512.06401/) (2025)

## Abstract (arXiv)

Compliance testing in highly regulated domains is crucial but largely manual, requiring domain experts to translate complex regulations into executable test cases. While large language models (LLMs) show promise for automation, their susceptibility to hallucinations limits reliable application. Existing hybrid approaches mitigate this issue by constraining LLMs with formal models, but still rely on costly manual modeling. To solve this problem, this paper proposes RAFT, a framework for requirements auto-formalization and compliance test generation via explicating tacit regulatory knowledge from multiple LLMs. RAFT employs an Adaptive Purification-Aggregation strategy to explicate tacit regulatory knowledge from multiple LLMs and integrate it into three artifacts: a domain meta-model, a formal requirements representation, and testability constraints. These artifacts are then dynamically injected into prompts to guide high-precision requirement formalization and automated test generation. Experiments across financial, automotive, and power domains show that RAFT achieves expert-level performance, substantially outperforms state-of-the-art (SOTA) methods while reducing overall generation and review time.