Health misinformation detection: search challenges, annotation issues and reliability of LLMs (Keynote) David E. Losada Universidad de Santiago de Compostela, Centro Singular de Investigación en Tecnoloxías Intelixentes, Spain Abstract As part of ROMCIR 2024, the 4th Workshop on Reducing Online Misinformation through Credible Information Retrieval, Prof. David E. Losada was invited to give a Keynote Speech discussing the current challenges related to the problem of health misinformation. The abstract of the speech follows. In this presentation, I will share insights from our work at CiTIUS (Centro Singular de Investigación en Tecnoloxías Intelixentes, Universidad de Santiago de Compostela, Spain) on the development of tech- nological and scientific solutions for detecting health misinformation. I will delve into the complexities of developing a multi-faceted retrieval system for misinformation detection that integrates multiple content-based features. The challenges of creating robust credibility benchmarks, given the subjective nature of credibility, will also be discussed. Lastly, I will share our recent efforts to evaluate the quality of LLMs’ responses to health-related queries. More details can be found on the ROMCIR 2024 website: https://romcir.disco.unimib.it/. Keywords Health misinformation, Credibility, Information Retrieval, Evaluations, Large Language Models ROMCIR 2024: The 4th Workshop on Reducing Online Misinformation through Credible Information Retrieval (held as part of ECIR 2024: the 46th European Conference on Information Retrieval), March 24, 2024, Glasgow, UK Envelope-Open david.losada@usc.es (D. E. Losada) GLOBE https://citius.gal/team/david-enrique-losada-carril/ (D. E. Losada) Orcid 0000-0001-8823-7501 (D. E. Losada) © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR ceur-ws.org Workshop ISSN 1613-0073 Proceedings