Projects

SpaceBenchRAG: A Multimodal, Multilingual Benchmark for KG-grounded RAG over Diverse Geographies

The project SpatialBenchRAG introduces the first multimodal, multilingual benchmark for evaluating Retrieval-Augmented Generation (RAG) systems grounded in spatial Knowledge Graphs (KGs). Addressing the lack of standardized resources for spatial reasoning, the benchmark combines diverse geographic datasets, including OpenStreetMap and Wikidata, to support realistic, context-aware evaluation across tasks such as spatial question answering, multi-hop reasoning, and visual queries By enabling transparent and reproducible research, this initiative aims to accelerate the development of geographically grounded AI systems for applications like disaster response, geo-aware assistants, and spatial fact-checking.

Co-Investigators: Martin Böckling (University of Mannheim), Heiko Paulheim (University of Mannheim)

Funded by the Open Science Office.

ReNewRS: Responsible News Recommender Systems

I’ve worked in the ReNewRS project throughout my PhD. ReNewRS is an interdisciplinary collaboration, combining media and communication studies, data science, and business informatics. It aims to investigate the influence of algorithmic news selection on shaping public opinion. This involves examining the occurrence of filter bubbles through news recommender systems and their effects on users’ opinion formation in a series of experimental studies. The objective is to gain empirical insights into how news recommender systems should be configured in order to mitigate potential polarizing effects and to develop guidelines for responsible news recommender systems that enable a more balanced opinion formation.

Find more information about our project here.