A Review on the Use of Large Language Models in the Context of Open Government Data

Abstract

Since ChatGPT was released to the public in 2022, large language models (LLM) have drawn enormous interest from academia and industry alike. Their ability to create complex texts based on provided inputs positions them to be a valuable tool in many domains. Moreover, since some time, many governments want to increase transparency and enable the offering of new services by making their data freely available. However, these efforts towards Open Government Data (OGD) face various challenges with many being related to the question how the data can be made easily findable and accessible. To address this issue, the use of LLMs appears to be a promising solution. To provide an overview of the corresponding research, in this work, the results of a structured literature review on the use of LLMs in the context of OGD are presented. Hereby, numerous application areas as well as challenges were identified and described, providing researchers and practitioners alike with a synoptic overview of the domain.