aiqbench analysis
This paper proposes a method for automated regulatory compliance checking. It represents regulations as a policy graph and case facts as a context graph, then aligns them to judge whether requirements are met. Reported MCC scores on three benchmarks exceed the strongest compared baselines, though the abstract gives no detail on the baselines or the evaluation setup. Readers should look at the ablations and code release to judge whether the gains hold up beyond these datasets.
GraphCompliance: Structure-Aware Regulatory Compliance through Policy-Context Graph Alignment
arXiv:2510.26309v2 Announce Type: replace Abstract: Regulatory compliance is an important requirement in many industrial and administrative settings. Yet compliance assessment remains difficult because regulatory requirements are distributed across structured documents and may depend on hierarchy, definitions, conditions, and cross-references, while the evidence relevant to a particular requirement may be embedded among multiple interacting actors, events, objects, and conditions in the assessed context. We present GraphCompliance, a structure-aware framework that represents regulatory documents as a schema-guided Policy Graph and contextual information as a Context Graph of entity-relation triples. GraphCompliance aligns the two graphs through a Compliance Gate, which identifies relevant regulatory requirements and evaluates them against the corresponding contextual evidence. This design makes regulatory structure explicit while organizing contextual facts into a comparable form, helping preserve structural dependencies and reduce terminology mismatch across different regulatory settings. Evaluation on EU2UK, GDPR-13, and CONTRACT yields Matthews correlation coefficients (MCC) of 0.802, 0.682, and 0.793, respectively. These values are numerically higher than those of the strongest compared methods on all three datasets. Ablation results further show that the key components of GraphCompliance contribute to its overall performance. These results support the utility of structured policy-context alignment for compliance-related prediction across heterogeneous regulatory settings. The source code of GraphCompliance is available at https://github.com/CHUNG-JiSeong/GraphCompliance.git.
Abstract:Regulatory compliance is an important requirement in many industrial and administrative settings. Yet compliance assessment remains difficult because regulatory requirements are distributed across structured documents and may depend on hierarchy, definitions, conditions, and cross-references, while the evidence relevant to a particular requirement may be embedded among multiple interacting actors, events, objects, and conditions in the assessed context. We present GraphCompliance, a structure-aware framework that represents regulatory documents as a schema-guided Policy Graph and contextual information as a Context Graph of entity-relation triples. GraphCompliance aligns the two graphs through a Compliance Gate, which identifies relevant regulatory requirements and evaluates them against the corresponding contextual evidence. This design makes regulatory structure explicit while organizing contextual facts into a comparable form, helping preserve structural dependencies and reduce terminology mismatch across different regulatory settings. Evaluation on EU2UK, GDPR-13, and CONTRACT yields Matthews correlation coefficients (MCC) of 0.802, 0.682, and 0.793, respectively. These values are numerically higher than those of the strongest compared methods on all three datasets. Ablation results further show that the key components of GraphCompliance contribute to its overall performance. These results support the utility of structured policy-context alignment for compliance-related prediction across heterogeneous regulatory settings. The source code of GraphCompliance is available at this https URL.
We acknowledge Makoto Onizuka and Sungmok Kim's contributions to v1. This version substantially reformulates the research question, assumptions, and conceptual framing, with revised methodology and evaluation. Following a reassessment of contributions to this version, authorship was revised with written consent from all v1 authors, including those no longer listed. Submitted to IEEE Access
Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
arXiv:2510.26309 [cs.AI]
(or arXiv:2510.26309v2 [cs.AI] for this version)
From: Jiseong Chung Mr. [view email] [v1] Thu, 30 Oct 2025 09:53:16 UTC (3,519 KB) [v2] Thu, 8 Oct 2026 19:50:38 UTC (2,536 KB)
Full text under the publisher's open licence · 296 words
Related coverage
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026
Assessing Information Ecosystems : How Governments Can Get Ahead of Hybrid Threats
carnegieendowment.org · Aug 5, 2026
Links #5: 2026/07
LessWrong · Jul 31, 2026
Article: Governing AI in the Cloud: A Practical Guide for Architects
InfoQ · Jun 15, 2026