The Decision Support Systems (DSS) Journal has published the paper "Effective use of open data story authoringportals for enterprises".social good: Design principles for explainable LLM-based open data assistants". The paper is co-authored Till Carlo Schelhorn, Ulrich Gnewuch, and Alexander Maedche from the Institute for Information Systems (WIN), human-centered systems lab (h-lab) and the University of Passau. 

Public access to information through open data is critical for achieving the United Nations’ Sustainable Development Goal 16, which promotes accountable and inclusive institutions. However, open data portals often present barriers, such as complex user interfaces and large data catalogs. In this paper, we conducted a two-cycle design science research project, guided by the theory of effective use, to design an explainable large language model (LLM)-based open data assistant. We evaluated the final artifact through a large-scale online experiment with 223 U.S. citizens using official Texas open data and synthesize our findings in two design principles.   

The paper is online available here: https://www.sciencedirect.com/science/article/abs/pii/S0167923626000874