Metraipolis › archive › dc_e3323f180cc7

Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code — arXiv:2609.19199

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19199
License (as archived)
CC0-1.0
Archived
2026-10-10T03:22:30.266Z
SHA-256 of the archived text
131de7c92e1bfd51fea8840c7d8b98b3cd2b58866a2a51ed252e4687a204de58
Stable URL of this page
https://metraipolis.com/documento/dc_e3323f180cc7

How to cite

Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code — arXiv:2609.19199 — arXiv (en), https://arxiv.org/abs/2609.19199 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3323f180cc7 (Metraipolis archive dc_e3323f180cc7, sha256 131de7c92e1bfd51fea8840c7d8b98b3cd2b58866a2a51ed252e4687a204de58)
BibTeX
@misc{dce3323f180cc7,
  title = {Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code — arXiv:2609.19199},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19199},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3323f180cc7; sha256 131de7c92e1bfd51fea8840c7d8b98b3cd2b58866a2a51ed252e4687a204de58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19199. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) are increasingly adopted for compliance and legal reasoning tasks, yet their outputs often lack explicit grounding in legal logic and evidence. We present Code-as-Auditor, an LLM-based framework that extends the model's reasoning capability toward structured and evidence-grounded compliance assessment. The framework translates regulatory information into (1) formalized checklists and executable decision trees, encoding regulations and conditions as interpretable code structures. During inference, each checklist item is (2) dynamically expanded into factual and counterfactual questions, guiding the model to reason over case-specific evidence and potential violations. This process establishes a reasoning pipeline that proceeds from evidence identification, through rule application, to final decision-making, while a self-verification loop improves the logical consistency of the generated code and the traceability of outcomes. Experiments on privacy and data protection scenarios demonstrate that Code-as-Auditor delivers more accurate and evidence-backed evaluations, enabling automated compliance regulation checking grounded in explicit regulatory criteria.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.19199 — 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 2026-10-10T03:04:13.770Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).