PolicyKG: An Agentic LLM Pipeline for Translating Institutional Policies into SHACL Knowledge Graphs
Institutional policies stay in natural language while the systems that check compliance demand machine-readable constraints. Bridging that gap is still done by hand. PolicyKG closes the loop. It is an LLM pipeline that reads a policy PDF, classifies each sentence as an obligation, permission, or prohibition, lifts the label into first-order deontic logic, and emits SHACL constraints. Four stages run on a LangGraph state machine with per-stage validators. The piece that matters most is the Corpus
Record details
Published: 10 August 2026
Source: arXiv
Category: Research
Topics: Regulation · Agents & autonomy
Retrieved: 11 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Context Is Not Authority: Structured Runtime Governance for Financial Market Agents
arXiv · 10 August 2026
OpenLoopEvolve: A Verifiable Self-Evolution Framework for Loop Policies in Long-Horizon Complex Tasks
arXiv · 10 August 2026
Preview-Based Relative-Motion Control of an Insertion Tool for Neural-Thread Placement in Pulsating Tissue
arXiv cs.HC · 9 August 2026
The Politician, the Liar, and the Obedient Worker: Emerging Behavior of LLM Agents in Hierarchical Games
arXiv · 10 August 2026
SocialFiVis: A Visual Analytics Sandbox for LLM-Grounded Multi-Agent Simulation in Social Finance
arXiv cs.HC · 9 August 2026
Business Arena: Benchmarking LLM Agents in a Realistic Marketplace
HuggingFace Daily Papers · 8 August 2026
How to cite this record
ethics.ai (10 August 2026), “PolicyKG: An Agentic LLM Pipeline for Translating Institutional Policies into SHACL Knowledge Graphs,” evidence record 18036, https://ethics.ai/record/18036 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.