Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning
On the map: LLM reasoning → Reasoning for agents, planning and code
Abstract (arXiv)
The risks posed by AI features are increasing as they are rapidly integrated into software applications. In response, regulations and standards for safe and secure AI have been proposed. In this paper, we present an agentic framework that constructs knowledge graphs (KGs) from AI policy documents and retrieves policy-relevant information to answer questions. We build KGs from three AI risk-related polices under two ontology schemas, and then evaluate five LLMs on 42 policy QA tasks spanning six reasoning types, from entity lookup to cross-policy inference, using both heuristic scoring and an LLM-as-judge. KG augmentation improves scores for all five models, and an open, LLM-discovered schema matches or exceeds the formal ontology.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 19 of its 41 references that are in the map. First posted on arXiv 30 Apr 2026.
Builds on
19 of 41 references.
Closest ancestors · 1
Same direction, newest first
- 2023LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models20 Aug
Other references · 18
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
- 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
- 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunitiescited by 97
- 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 80
- 2025KGGen: Extracting Knowledge Graphs from Plain Text with Language Modelscited by 49
- 2020PolicyQA: A Reading Comprehension Dataset for Privacy Policiescited by 34
- 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 31
- 2024Large Language Models Can Better Understand Knowledge Graphs Than We Thoughtcited by 10
- 2025Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modellingcited by 9
6 more
- 2025GraphCompliance: Structure-Aware Regulatory Compliance through Policy-Context Graph Alignmentcited by 9
- 2024Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Datacited by 6
- 2025KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphscited by 6
- 2025RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QAcited by 6
- 2024PrivComp-KG : Leveraging Knowledge Graph and Large Language Models for Privacy Policy Compliance Verificationcited by 2
- 2025Let's have a chat with the EU AI Actcited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026PolicyKG: An Agentic LLM Pipeline for Translating Institutional Policies into SHACL Knowledge Graphs
- 2025Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation
- 2025LLM-empowered knowledge graph construction: A survey
- 2026Toward Effective and Reliable LLM Agents via Dynamic Ontology
- 2026Policy-Invisible Violations in LLM-Based Agents
- 2025AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots
- 2026GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubrics
- 2025Increasing AI Explainability by LLM Driven Standard Processes