# ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection

arXiv: https://arxiv.org/abs/2604.23585 · HTML: https://mlsanity.com/paper/2604.23585/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [FinBERT: Financial Sentiment Analysis with Pre-trained Language Models](https://mlsanity.com/paper/1908.10063/) (2019)
- [LexGLUE: A Benchmark Dataset for Legal Language Understanding in English](https://mlsanity.com/paper/2110.00976/) (2021)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity](https://mlsanity.com/paper/2310.07521/) (2023)
- [Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering](https://mlsanity.com/paper/2306.04136/) (2023)
- [LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain](https://mlsanity.com/paper/2408.10343/) (2024)
- [Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset](https://mlsanity.com/paper/2207.00220/) (2022)
- [MultiLegalPile: A 689GB Multilingual Legal Corpus](https://mlsanity.com/paper/2306.02069/) (2023)
- [Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges](https://mlsanity.com/paper/2410.21306/) (2024)
- [A Dataset of German Legal Documents for Named Entity Recognition](https://mlsanity.com/paper/2003.13016/) (2020)
- [Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)](https://mlsanity.com/paper/2407.12858/) (2024)
- [NLP-based Automated Compliance Checking of Data Processing Agreements against GDPR](https://mlsanity.com/paper/2209.09722/) (2022)
- [Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations](https://mlsanity.com/paper/2101.10726/) (2021)
- [Agent-Specific Deontic Modality Detection in Legal Language](https://mlsanity.com/paper/2211.12752/) (2022)
- [CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation](https://mlsanity.com/paper/2508.05534/) (2025)

## Built on by (most cited first, 2 of 2)

- [Reverse Engineering Compliance: A Dual-Graph Verification Framework for Auditing Legacy IT Security Concepts](https://mlsanity.com/paper/2607.08292/) (2026)
- [Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems](https://mlsanity.com/paper/2610.12313/) (2026)

## Abstract (arXiv)

Financial institutions must track over 60,000 regulatory events annually, overwhelming manual compliance teams; the industry has paid over USD 300 billion in fines and settlements since the 2008 financial crisis. We present ComplianceNLP, an end-to-end system that automatically monitors regulatory changes, extracts structured obligations, and identifies compliance gaps against institutional policies. The system integrates three components: (1) a knowledge-graph-augmented RAG pipeline grounding generations in a regulatory knowledge graph of 12,847 provisions across SEC, MiFID II, and Basel III; (2) multi-task obligation extraction combining NER, deontic classification, and cross-reference resolution over a shared LEGAL-BERT encoder; and (3) compliance gap analysis that maps obligations to internal policies with severity-aware scoring. On our benchmark, ComplianceNLP achieves 87.7 F1 on gap detection, outperforming GPT-4o+RAG by +3.5 F1, with 94.2% grounding accuracy (r=0.83 vs. human judgments) and 83.4 F1 under realistic end-to-end error propagation. Ablations show that knowledge-graph re-ranking contributes the largest marginal gain (+4.6 F1), confirming that structural regulatory knowledge is critical for cross-reference-heavy tasks. Domain-specific knowledge distillation (70B → 8B) combined with Medusa speculative decoding yields 2.8× inference speedup; regulatory text's low entropy (H=2.31 bits vs. 3.87 general text) produces 91.3% draft-token acceptance rates. In four months of parallel-run deployment processing 9,847 updates at a financial institution, the system achieved 96.0% estimated recall and 90.7% precision, with a 3.1× sustained analyst efficiency gain. We report deployment lessons on trust calibration, GRC integration, and distributional shift monitoring for regulated-domain NLP.