Citation-Enforced RAG for Fiscal Document Intelligence: Cited, Explainable Knowledge Retrieval in Tax Compliance
This addresses the need for explainable and auditable AI in high-stakes regulatory domains like tax compliance, though it is incremental in applying existing RAG concepts with specific enhancements.
The paper tackled the problem of lacking transparency and citation fidelity in retrieval-augmented generation for tax compliance by proposing a citation-enforced RAG framework, resulting in improved citation fidelity and reduced hallucination on real IRS and state tax documents.
Tax authorities and public-sector financial agencies rely on large volumes of unstructured and semi-structured fiscal documents - including tax forms, instructions, publications, and jurisdiction-specific guidance - to support compliance analysis and audit workflows. While recent advances in generative AI and retrieval-augmented generation (RAG) have shown promise for document-centric question answering, existing approaches often lack the transparency, citation fidelity, and conservative behaviour required in high-stakes regulatory domains. This paper presents a multimodal, citation-enforced RAG framework for fiscal document intelligence that prioritises explainability and auditability. The framework adopts a source-first ingestion strategy, preserves page-level provenance, enforces citations during generation, and supports abstention when evidence is insufficient. Evaluation on real IRS and state tax documents demonstrates improved citation fidelity, reduced hallucination, and analyst-usable explanations, illustrating a pathway toward trustworthy AI for tax compliance.