GraphCompliance: Aligning Policy and Context Graphs for LLM-Based Regulatory Compliance
- URL: http://arxiv.org/abs/2510.26309v1
- Date: Thu, 30 Oct 2025 09:53:16 GMT
- Title: GraphCompliance: Aligning Policy and Context Graphs for LLM-Based Regulatory Compliance
- Authors: Jiseong Chung, Ronny Ko, Wonchul Yoo, Makoto Onizuka, Sungmok Kim, Tae-Wan Kim, Won-Yong Shin,
- Abstract summary: We introduce GraphCompliance, a framework that represents regulatory texts as a Policy Graph and runtime contexts as a Context Graph.<n>In experiments on 300-derived real-world scenarios, GraphCompliance yields 4.1-7.2 percentage points (pp) higher micro-F1 than LLM-only and RAG baselines.
- Score: 17.686657395022248
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Compliance at web scale poses practical challenges: each request may require a regulatory assessment. Regulatory texts (e.g., the General Data Protection Regulation, GDPR) are cross-referential and normative, while runtime contexts are expressed in unstructured natural language. This setting motivates us to align semantic information in unstructured text with the structured, normative elements of regulations. To this end, we introduce GraphCompliance, a framework that represents regulatory texts as a Policy Graph and runtime contexts as a Context Graph, and aligns them. In this formulation, the policy graph encodes normative structure and cross-references, whereas the context graph formalizes events as subject-action-object (SAO) and entity-relation triples. This alignment anchors the reasoning of a judge large language model (LLM) in structured information and helps reduce the burden of regulatory interpretation and event parsing, enabling a focus on the core reasoning step. In experiments on 300 GDPR-derived real-world scenarios spanning five evaluation tasks, GraphCompliance yields 4.1-7.2 percentage points (pp) higher micro-F1 than LLM-only and RAG baselines, with fewer under- and over-predictions, resulting in higher recall and lower false positive rates. Ablation studies indicate contributions from each graph component, suggesting that structured representations and a judge LLM are complementary for normative reasoning.
Related papers
- ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing [64.65742943745866]
ChartE$3$ is an End-to-End Chart Editing benchmark.<n>It directly evaluates models without relying on intermediate natural language programs or code-level supervision.<n>It contains over 1,200 high-quality samples constructed via a well-designed data pipeline with human curation.
arXiv Detail & Related papers (2026-01-29T13:29:27Z) - GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
arXiv Detail & Related papers (2025-10-06T08:09:15Z) - GRAFT: GRaPH and Table Reasoning for Textual Alignment -- A Benchmark for Structured Instruction Following and Visual Reasoning [0.0]
GRAFT is a structured multimodal benchmark for evaluating models on instruction-following visual reasoning, and visual-textual alignment.<n>It features generated charts and synthetically rendered tables, created with Python libraries to ensure control over data semantics, and clarity.
arXiv Detail & Related papers (2025-08-21T16:13:49Z) - RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA [0.0]
Regulatory compliance question answering (QA) requires precise, verifiable information.<n>We present a novel multi-agent framework that integrates a Knowledge Graph (KG) of Regulatory triplets with Retrieval-Augmented Generation (RAG)<n>Our hybrid system outperforms conventional methods in complex regulatory queries, ensuring factual correctness with embedded triplets.
arXiv Detail & Related papers (2025-08-13T15:51:05Z) - Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models [63.64507678113921]
We introduce Graph-KV, which governs interaction through structural inductive biases.<n>In this framework, 'target' segments selectively attend only to the KV-cache of their designated'source' segments.<n>We evaluate Graph-KV across three scenarios: (1) seven RAG benchmarks spanning direct inference, multi-hop reasoning, and long-document understanding; (2) Arxiv-QA, a novel academic paper QA task with full-text scientific papers structured as citation ego-graphs; and (3) paper topic classification within a citation network.
arXiv Detail & Related papers (2025-06-09T00:30:08Z) - Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation [36.166087396386445]
We present Compliance-to-Code, the first large-scale Chinese dataset dedicated to financial regulatory compliance.<n> Covering 1,159 annotated clauses from 361 regulations across ten categories, each clause is modularly structured with four logical elements-subject, condition, constraint, and contextual information-along with regulation relations.<n>We provide deterministic Python code mappings, detailed code reasoning, and code explanations to facilitate automated auditing.
arXiv Detail & Related papers (2025-05-26T10:38:32Z) - An Ontology-Driven Graph RAG for Legal Norms: A Structural, Temporal, and Deterministic Approach [0.0]
RAG systems in the legal domain face a critical challenge: standard, flat-text retrieval is blind to the hierarchical, diachronic, and causal structure of law, leading to anachronistic and unreliable answers.<n>This paper introduces the Structure-Aware Temporal Graph RAG (SAT-Graph RAG), an ontology-driven framework designed to overcome these limitations by explicitly modeling the formal structure and diachronic nature of legal norms.
arXiv Detail & Related papers (2025-04-29T18:36:57Z) - Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text
Documents via Semantic-Oriented Hierarchical Graphs [79.0426838808629]
We propose TAT-DQA, i.e. to answer the question over a visually-rich table-text document.
Specifically, we propose a novel Doc2SoarGraph framework with enhanced discrete reasoning capability.
We conduct extensive experiments on TAT-DQA dataset, and the results show that our proposed framework outperforms the best baseline model by 17.73% and 16.91% in terms of Exact Match (EM) and F1 score respectively on the test set.
arXiv Detail & Related papers (2023-05-03T07:30:32Z) - Unifying Graph Contrastive Learning with Flexible Contextual Scopes [57.86762576319638]
We present a self-supervised learning method termed Unifying Graph Contrastive Learning with Flexible Contextual Scopes (UGCL for short)
Our algorithm builds flexible contextual representations with contextual scopes by controlling the power of an adjacency matrix.
Based on representations from both local and contextual scopes, distL optimises a very simple contrastive loss function for graph representation learning.
arXiv Detail & Related papers (2022-10-17T07:16:17Z) - FactGraph: Evaluating Factuality in Summarization with Semantic Graph
Representations [114.94628499698096]
We propose FactGraph, a method that decomposes the document and the summary into structured meaning representations (MRs)
MRs describe core semantic concepts and their relations, aggregating the main content in both document and summary in a canonical form, and reducing data sparsity.
Experiments on different benchmarks for evaluating factuality show that FactGraph outperforms previous approaches by up to 15%.
arXiv Detail & Related papers (2022-04-13T16:45:33Z) - Similarity Reasoning and Filtration for Image-Text Matching [85.68854427456249]
We propose a novel Similarity Graph Reasoning and Attention filtration network for image-text matching.
Similarity Graph Reasoning (SGR) module relying on one graph convolutional neural network is introduced to infer relation-aware similarities with both the local and global alignments.
We demonstrate the superiority of the proposed method with achieving state-of-the-art performances on the Flickr30K and MSCOCO datasets.
arXiv Detail & Related papers (2021-01-05T06:29:35Z)
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.