David Kletz

David Kletz is a postdoctoral researcher at IDSIA, working within the Natural Language Processing (NLP) team. He earned his PhD in NLP in February 2025 from Sorbonne-Nouvelle and Université Paris Cité (UPC), where his research focused on the representation and understanding of negation in pre-trained language models. His current work explores the application of large language models (LLMs) to enhance information retrieval for specialized documents and domain-specific tasks. Building on his doctoral research, he remains deeply engaged in analyzing model knowledge and improving model interpretability, aiming to make AI systems more transparent and explainable.

• ORCID
• Google Scholar
• Semantic Scholar

• Sandra Mitrović, Joseph Cornelius, David Kletz, Ljiljana Dolamic, and Fabio Rinaldi. 2025. Swushroomsia at SemEval-2025 Task 3: Probing LLMs’ Collective Intelligence for Multilingual Hallucination Detection. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 1810–1827, Vienna, Austria. Association for Computational Linguistics.
• David Kletz, Pascal Amsili, and Marie Candito. 2025. Polarity inversion operators in PLM. In Proceedings of the 29th Conference on Computational Natural Language Learning, pages 312–322, Vienna, Austria. Association for Computational Linguistics.
• Sandra Mitrović, Joseph Cornelius, David Kletz, Ljiljana Dolamic, and Fabio Rinaldi. Presenting LLMs’ Collective Intelligence Approach for Multilingual Hallucination Detection. In Proceedings of the 9th edition of the Swiss Text Analytics Conference.

E-Mail: david.kletz AT supsi.ch

NLP group page