A curated ontology prompt with self-correction rules lets GPT-4 convert natural language instructions into ODRL usage policies with up to about 92% benchmark accuracy.
Policy Patterns for Usage Control in Data Spaces
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Data-driven technologies have the potential to initiate a transportation related revolution in the way we travel, commute and navigate within cities. As a major effort of this transformation relies on Mobility Data Spaces for the exchange of mobility data, the necessity to protect valuable data and formulate conditions for data exchange arises. This paper presents key contributions to the development of automated contract negotiation and data usage policies in the Mobility Data Space. A comprehensive listing of policy patterns for usage control is provided, addressing common requirements and scenarios in data sharing and governance. The use of the Open Digital Rights Language (ODRL) is proposed to formalize the collected policies, along with an extension of the ODRL vocabulary for data space-specific properties.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
From Instructions to ODRL Usage Policies: An Ontology Guided Approach
A curated ontology prompt with self-correction rules lets GPT-4 convert natural language instructions into ODRL usage policies with up to about 92% benchmark accuracy.