From Instructions to ODRL Usage Policies: An Ontology Guided Approach

TL;DR

This paper introduces an ontology-guided method leveraging GPT-4 to automatically generate ODRL usage policies from natural language instructions, improving accuracy in complex data exchange scenarios.

Contribution

It presents a novel approach that uses curated ontology documentation and heuristics to guide large language models in policy generation, with a focus on ODRL and dataspaces.

Findings

Achieved up to 91.95% accuracy in knowledge graph generation.

Demonstrated effectiveness across 12 diverse use cases.

Showed that curated ontology documentation enhances policy generation.

Abstract

This study presents an approach that uses large language models such as GPT-4 to generate usage policies in the W3C Open Digital Rights Language ODRL automatically from natural language instructions. Our approach uses the ODRL ontology and its documentation as a central part of the prompt. Our research hypothesis is that a curated version of existing ontology documentation will better guide policy generation. We present various heuristics for adapting the ODRL ontology and its documentation to guide an end-to-end KG construction process. We evaluate our approach in the context of dataspaces, i.e., distributed infrastructures for trustworthy data exchange between multiple participating organizations for the cultural domain. We created a benchmark consisting of 12 use cases of varying complexity. Our evaluation shows excellent results with up to 91.95% accuracy in the resulting knowledge graph.