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

• URL: http://arxiv.org/abs/2604.23585v1
• Date: Sun, 26 Apr 2026 07:44:50 GMT
• Title: ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection
• Abstract summary: Financial institutions track over 60,000 regulatory events annually.<n>The industry has paid over USD 300 billion in fines and settlements since the 2008 financial crisis.<n>We present ComplianceNLP, an end-to-end system that automatically monitors regulatory changes, extracts structured obligations, and identifies compliance gaps.
• Score: 13.891522069967507
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 $\to$ 8B) combined with Medusa speculative decoding yields $2.8\times$ 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 $3.1\times$ sustained analyst efficiency gain. We report deployment lessons on trust calibration, GRC integration, and distributional shift monitoring for regulated-domain NLP.

Related papers

• Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection [66.44527094471619]
  We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns.<n>On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-09-15T00:31:01Z)
• RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting [83.06074370551887]
  A fixed context window is mismatched to the time-varying optimal look-back of non-stationary price processes.<n>We propose a Mixture-of-Experts framework designed to adaptively determine the temporal context for each input sample.<n> Experiments on cumulative log-return prediction (HS300, S&P500) and fund sales forecasting demonstrate that RAVEN achieves SOTA performances, improves Pearson correlation by 9.2% on HS300 and 20.2% on S&P500, and reduces MSE by 18.2% on fund sales forecasting.
  arXiv  Detail & Related papers  (2026-06-23T02:11:04Z)
• YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition [78.52944812151664]
  Large language models (LLMs) drive significant financial innovations, yet their deployment is bottlenecked by KV cache memory overhead.<n>We propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline built on the Huawei Ascend ecosystem.
  arXiv  Detail & Related papers  (2026-06-04T08:44:37Z)
• SCAFDS: Edge-Feature Graph Attention for Interbank Fraud Detection with Attribution-Grounded SAR Generation [0.40611352512781873]
  The U.S. financial system processes approximately 1.3 million interbank transactions daily.<n>No system in the reviewed literature models fraud propagation across the interbank network using fraud co-occurrence edge features.<n>This paper introduces SCAFDS (Systemic Contagion-Aware Fraud Detection System), a seven-stage integrated surveillance pipeline.
  arXiv  Detail & Related papers  (2026-05-17T21:04:30Z)
• TRUST: A Framework for Decentralized AI Service v.0.1 [47.384270414446604]
  Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification.<n>We introduce TRUST (Transparent, Robust, and Unified Services for Trustworthy AI), a decentralized framework with three innovations.<n>We prove a Safety-Profitability Theorem ensuring honest auditors profit while malicious actors incur losses.
  arXiv  Detail & Related papers  (2026-04-29T19:32:58Z)
• FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification [13.891522069967507]
  FinGround is a verify-then-ground pipeline for financial document QA.<n> Stage 1 performs finance-aware hybrid retrieval over text and tables.<n> Stage 2 decomposes answers into atomic claims classified by a six-type financial taxonomy.<n> Stage 3 rewrites unsupported claims with paragraph- and table-cell-level citations.
  arXiv  Detail & Related papers  (2026-04-26T07:52:59Z)
• Explainable Graph Neural Networks for Interbank Contagion Surveillance: A Regulatory-Aligned Framework for the U.S. Banking Sector [0.40611352512781873]
  The ST-GAT framework was created to serve as an explainable GNN-based solution for detecting bank distress early warning signs.<n>It models 8,103 FDIC insured institutions across 58 quarterly snapshots (2010Q1-2024Q2)<n>The framework achieves the highest AUPRC among all GNN architectures.
  arXiv  Detail & Related papers  (2026-04-14T19:07:28Z)
• Shapley Value-Guided Adaptive Ensemble Learning for Explainable Financial Fraud Detection with U.S. Regulatory Compliance Validation [0.34376560669160394]
  Financial crime costs U.S. institutions over $32 billion each year.<n>Many AI tools for fraud detection operate as black boxes that cannot provide transparent, auditable explanations.<n>This study offers a thorough evaluation of explanation quality across faithfulness and stability.
  arXiv  Detail & Related papers  (2026-04-14T19:00:20Z)
• A Regulatory Governance Framework for AI-Driven Financial Fraud Detection in U.S. Banking: Integrating OCC, SR 11-7, CFPB, and FinCEN Compliance Requirements for Model Development, Validation, and Monitoring Lifecycles [0.40611352512781873]
  This paper presents the Regulatory Governance Framework for AI-Driven Financial Fraud Detection (RGF-AFFD)<n>It is a three-tier governance architecture empirically anchored in a multi-study empirical program.<n>The RGF-AFFD is the first integrated deployment blueprint to simultaneously satisfy OCC, SR 11-7, CFPB, and FinCEN requirements.
  arXiv  Detail & Related papers  (2026-04-14T08:30:04Z)
• FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systems [0.0]
  Current Knowledge Graph (KG)-augmented QA systems lack systematic mechanisms to detect hallucinations.<n>We introduce FinBench-QA-Hallucination, a benchmark for evaluating hallucination detection methods in KG-augmented financial QA over SEC 10-K filings.<n>Our findings highlight vulnerabilities in current KG-augmented systems and provide insights for building reliable financial information systems.
  arXiv  Detail & Related papers  (2026-03-11T04:37:53Z)
• Scalable Multi-Task Low-Rank Model Adaptation [43.22544779625565]
  Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation.<n>We find that existing solutions, like regularization and dynamic routing, fail at scale because they are constrained by a fundamental trade-off.<n>We propose mtLoRA, a scalable solution with three novel designs.
  arXiv  Detail & Related papers  (2026-03-02T06:57:11Z)
• PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering [71.15346406323827]
  We introduce PRIME, a benchmark for evaluating verifiers on Process-Outcome Alignment verification.<n>We find that current verifiers frequently fail to detect derivation flaws.<n>We propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
  arXiv  Detail & Related papers  (2026-02-12T04:45:01Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement Learning [43.06827300023392]
  STREAM-RL is an Uncertainty-Guided Adaptive Conformal Forecaster, a Conformal Residual Flow Network, and an Uncertainty-Guided Safe World-Model RL agent.<n>Experiments on multiple real-world traffic trajectory data demonstrate that STREAM-RL achieves 91.4% coverage efficiency, controls FDR at 4.1% under verified dependence, and improves safety rate to 95.2% compared to 69% for standard PPO.
  arXiv  Detail & Related papers  (2026-02-04T18:10:59Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• LLM Output Drift: Cross-Provider Validation & Mitigation for Financial Workflows [0.5798758080057375]
  Nondeterministic outputs (output drift) undermine auditability and trust.<n>We quantify drift across five model architectures on regulated financial tasks.<n>This finding challenges conventional assumptions that larger models are universally superior for production deployment.
  arXiv  Detail & Related papers  (2025-11-10T19:54:00Z)

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.