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

• URL: http://arxiv.org/abs/2603.14170v1
• Date: Wed, 11 Mar 2026 20:01:35 GMT
• Title: Citation-Enforced RAG for Fiscal Document Intelligence: Cited, Explainable Knowledge Retrieval in Tax Compliance
• Abstract summary: This paper presents a citation-enforced RAG framework for fiscal document intelligence that prioritises explainability and auditability.<n> Evaluation on real IRS and state tax documents demonstrates improved citation fidelity, reduced provenance, and analyst-usable explanations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering [54.97384993676565]
  We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from complex national R&D regulations.<n>RefWalk traverses cross-document citations, fuses multi-view candidates via max-based aggregation, and enforces per-rule attribution to explicitly map claims to sources.
  arXiv  Detail & Related papers  (2026-05-28T10:38:38Z)
• Compliance-by-Construction Argument Graphs: Using Generative AI to Produce Evidence-Linked Formal Arguments for Certification-Grade Accountability [0.0]
  This paper proposes a compliance-by-construction architecture that integrates Generative AI (GenAI) with structured formal argument representations.<n>The architecture treats each AI-assisted step as a claim that must be supported by verifiable evidence and validated against explicit reasoning constraints.<n>The analysis suggests that validation rules can prevent unsupported claims from entering the decision record while allowing GenAI to accelerate argument construction.
  arXiv  Detail & Related papers  (2026-04-05T12:55:16Z)
• CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era [51.63024682584688]
  Large language models (LLMs) introduce a new risk: fabricated references that appear plausible but correspond to no real publications.<n>We present the first comprehensive benchmark and detection framework for hallucinated citations in scientific writing.<n>Our framework significantly outperforms prior methods in both accuracy and interpretability.
  arXiv  Detail & Related papers  (2026-02-26T19:17:39Z)
• HalluGraph: Auditable Hallucination Detection for Legal RAG Systems via Knowledge Graph Alignment [0.0]
  We introduce HalluGraph, a graph-theoretic framework that quantifies hallucinations through structural alignment between knowledge graphs extracted from context, query, and response.<n>Our approach produces bounded, interpretable metrics into textitEntity Grounding (EG), measuring whether entities in the response appear in source documents, and textitRelation Preservation (RP), verifying that asserted relationships are supported by context.
  arXiv  Detail & Related papers  (2025-12-01T13:31:06Z)
• A Taxonomy-Driven Case Study of Australian Web Resources Against Technology-Facilitated Abuse [7.412243627099252]
  Technology-Facilitated Abuse (TFA) encompasses a broad and rapidly evolving set of behaviours in which digital systems are used to harass, monitor, threaten, or control individuals.<n>This paper contributes a unified, literature-derived taxonomy of TFA grounded in a structured review of peer-reviewed studies.<n>It is the first large-scale, taxonomy-aligned audit of institutional web resources in Australia.
  arXiv  Detail & Related papers  (2025-11-28T01:02:54Z)
• SemanticCite: Citation Verification with AI-Powered Full-Text Analysis and Evidence-Based Reasoning [0.0]
  We introduce SemanticCite, an AI-powered system that verifies citation accuracy through full-text source analysis.<n>Our approach combines multiple retrieval methods with a four-class classification system that captures nuanced claim-source relationships.<n>We contribute a comprehensive dataset of over 1,000 citations with detailed alignments, functional classifications, semantic annotations, and bibliometric metadata.
  arXiv  Detail & Related papers  (2025-11-20T10:05:21Z)
• The Journal of Prompt-Engineered Philosophy Or: How I Started to Track AI Assistance and Stopped Worrying About Slop [0.0]
  Article analyzes how incentives discourage transparency in precisely the work where it matters most.<n>Traditional venues cannot resolve this tension through policy tweaks alone, as the underlying prestige economy rewards opacity.<n>It proposes an alternative publishing infrastructure: a venue outside prestige systems that enforces mandatory disclosure, enables reproduction-based review, and supports ecological validity through detailed documentation.
  arXiv  Detail & Related papers  (2025-11-10T08:56:21Z)
• VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification [107.75781898355562]
  We introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution.<n>We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.
  arXiv  Detail & Related papers  (2025-10-13T13:38:54Z)
• ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search [69.60882125603133]
  We present ReliabilityRAG, a framework for adversarial robustness that explicitly leverages reliability information of retrieved documents.<n>Our work is a significant step towards more effective, provably robust defenses against retrieved corpus corruption in RAG.
  arXiv  Detail & Related papers  (2025-09-27T22:36:42Z)
• Generative AI for FFRDCs [2.132096006921048]
  We show how large language models can accelerate summarization, classification, extraction, and sense-making with only a few input-output examples.<n>To enable use in sensitive government contexts, we apply OnPrem$.$LLM, an open-source framework for secure and flexible application of generative AI.
  arXiv  Detail & Related papers  (2025-09-25T11:45:39Z)
• DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding [66.07724324530844]
  We propose DocThinker, a rule-based Reinforcement Learning framework for dynamic inference-time reasoning.<n>Our method mitigates catastrophic forgetting and enhances both adaptability and transparency.<n>Our findings highlight RL as a powerful alternative for enhancing explainability and adaptability in MLLM-based document understanding.
  arXiv  Detail & Related papers  (2025-08-12T03:06:55Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.