Towards Real-World Fact-Checking with Large Language Models

Keynote by Iryna Gurevych at the 4th TAILOR conference

Iryna Gurevych, professor of Computer Science and director of the Ubiquitous Knowledge Processing Lab at the Technical University of Darmstadt in Germany will give a keynote at the closing session of the 4th TAILOR conference “Trustworthy AI from Lab to market”, 4-5 June 2024, Lisbon. Her talk will be about misinformation and fact checking with LLM:s.

Abstract

Misinformation poses a growing threat to our society. It has a severe impact on public health by promoting fake cures or vaccine hesitancy, and it is used as a weapon during military conflicts to spread fear and distrust. Current natural language processing (NLP) fact-checking research focuses on identifying evidence and the veracity of a claim. People’s beliefs however often do not depend on the claim and the rational reasoning as such, but on credible content that makes the claim seem more reliable, such as scientific publications or visual content that was manipulated or stems from unrelated context. To combat misinformation we need to show (1) “Why was the claim believed to be true?”, (2) “Why is the claim false?”, (3) “Why is the alternative explanation correct?”. In the talk, I will zoom into two critical aspects of such misinformation supported by credible though misleading content. First, I will present our efforts to dismantle misleading narratives based on fallacious interpretations of scientific publications. Second, I will show how we can use multimodal large language models to (1) detect misinformation based on visual content, (2) provide strong alternative explanations for the visual content.

Biography

Iryna Gurevych (PhD 2003, U. Duisburg-Essen, Germany) is professor of Computer Science and director of the Ubiquitous Knowledge Processing (UKP) Lab at the Technical University of Darmstadt in Germany. In addition, she is an adjunct professor at MBZUAI in Abu-Dhabi, UAE and an affiliated professor at INSAIT in Sofia, Bulgaria. Her main research interests are in machine learning for large-scale language understanding and text semantics. Iryna’s work has received numerous awards. Those include the ACL fellow award 2020, the first-ever Hessian LOEWE Distinguished Chair award (2,5 mil. Euro) in 2021 and an ERC Advanced Grant in 2022 (2,5 Mil. Euro). Iryna is co-director of the NLP program within ELLIS, a European network of excellence in machine learning. She is the recent president of the Association for Computational Linguistics (ACL).