Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation

TL;DR

This paper introduces Compliance-to-Code, a large-scale Chinese dataset for financial compliance code generation, and demonstrates its utility through a pipeline that structures regulations, generates code, and produces audit reports.

Contribution

It presents the first Chinese dataset for financial compliance code generation, addressing language and domain gaps in existing datasets, and develops a pipeline for automated compliance auditing.

Findings

The dataset covers 1,159 clauses from 361 regulations across ten categories.

The pipeline effectively structures regulations, generates code, and produces audit reports.

Demonstrates improved automation in financial compliance checking.

Abstract

Nowadays, regulatory compliance has become a cornerstone of corporate governance, ensuring adherence to systematic legal frameworks. At its core, financial regulations often comprise highly intricate provisions, layered logical structures, and numerous exceptions, which inevitably result in labor-intensive or comprehension challenges. To mitigate this, recent Regulatory Technology (RegTech) and Large Language Models (LLMs) have gained significant attention in automating the conversion of regulatory text into executable compliance logic. However, their performance remains suboptimal particularly when applied to Chinese-language financial regulations, due to three key limitations: (1) incomplete domain-specific knowledge representation, (2) insufficient hierarchical reasoning capabilities, and (3) failure to maintain temporal and logical coherence. One promising solution is to develop a domain specific and code-oriented datasets for model training. Existing datasets such as LexGLUE, LegalBench, and CODE-ACCORD are often English-focused, domain-mismatched, or lack fine-grained granularity for compliance code generation. To fill these gaps, we present Compliance-to-Code, the first large-scale Chinese dataset dedicated to financial regulatory compliance. Covering 1,159 annotated clauses from 361 regulations across ten categories, each clause is modularly structured with four logical elements-subject, condition, constraint, and contextual information-along with regulation relations. We provide deterministic Python code mappings, detailed code reasoning, and code explanations to facilitate automated auditing. To demonstrate utility, we present FinCheck: a pipeline for regulation structuring, code generation, and report generation.