Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911636165492736 |
|---|---|
| author | Baldwin, Wilder Ghanavati, Sepideh |
| author_facet | Baldwin, Wilder Ghanavati, Sepideh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27713 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning Baldwin, Wilder Ghanavati, Sepideh Artificial Intelligence 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. |
| title | Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.27713 |