At the 10th International Summer School on AI and Big Data, Prof. Martin Potthast will give a presentation oin the field of Generative AI and Machine Learning.

Talk: Evaluating Generative Retrieval Systems

Information retrieval is once again at a turning point in its long history: texts and images that used to be retrieved exclusively from collections of existing documents can now be synthesized on query. Thanks to recent advances in generative AI in general and large language models (LLMs) in particular, searchers can expect to be relieved of the manual task of identifying the relevant parts of retrieved documents and instead receive answers in the form of text or multimedia documents. This upheaval runs parallel to the perceived deterioration in the quality of results from traditional web search engines. For years, social media users have been complaining about the low relevance of search results from major search engines. In this respect, generative AI could play a key role in a renaissance of information retrieval. However, it also poses new challenges that require a new framework for researching, developing and evaluating such technologies.

Bio

Martin Potthast holds the hessian.AI Chair for Deep Semantic Learning at the University of Kassel. His research focuses on language technologies, search engines and the analysis and synthesis of information. Martin contributes to the research areas of information retrieval, natural language processing, and artificial intelligence.

Martin Potthast studied computer science at the University of Paderborn (2001-2006) and successfully completed his doctorate at the Bauhaus University Weimar in December 2011, where he then worked as a postdoctoral researcher at the Digital Bauhaus Lab. In October 2017 he was appointed junior professor at Leipzig University and in October 2023 full professor, thus successfully completing his tenure track. Martin is a founding member and board member of the ScaDS.AI Center for Scalable Data Analytics and Artificial Intelligence. In April 2024, he was appointed Professor of Deep Semantic Learning at the University of Kassel and joined the Hessian Center for Artificial Intelligence hessian.AI.