Citation-Enforced RAG for Fiscal Document Intelligence: Cited, Explainable Knowledge Retrieval in Tax Compliance

TL;DR

This paper introduces a citation-enforced RAG framework for fiscal document analysis that enhances transparency, citation accuracy, and explainability in AI-driven tax compliance workflows.

Contribution

It proposes a multimodal, source-first RAG approach with citation enforcement and provenance preservation tailored for high-stakes fiscal document analysis.

Findings

Improved citation fidelity and reduced hallucination in document QA

Enhanced explainability and auditability for tax authorities

Effective handling of IRS and state tax documents

Abstract

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.