Overview of Touché 2025: Argumentation Systems Extended Abstract

Open Access
Authors
  • Johannes Kiesel
  • Çağrı Çöltekin
  • Marcel Gohsen
  • Sebastian Heineking
  • Maximilian Heinrich
  • Maik Fröbe
  • Tim Hagen
  • Mohammad Aliannejadi ORCID logo
  • Tomaž Erjavec
  • Matthias Hagen
  • Matyáš Kopp
  • Nikola Ljubešić
  • Katja Meden
  • Nailia Mirzakhmedova
  • Vaidas Morkevičius
  • Harrisen Scells
  • Ines Zelch
  • Martin Potthast
  • Benno Stein
Publication date 2025
Host editors
  • Claudia Hauff
  • Craig Macdonald
  • Dietmar Jannach
  • Gabriella Kazai
  • Franco Maria Nardini
  • Fabio Pinelli
  • Fabrizio Silvestri
  • Nicola Tonellotto
Book title Advances in Information Retrieval
Book subtitle 47th European Conference on Information Retrieval, ECIR 2025, Lucca, Italy, April 6–10, 202 : proceedings
ISBN
  • 9783031887192
ISBN (electronic)
  • 9783031887208
Series Lecture Notes in Computer Science
Event 47th European Conference on Information Retrieval, ECIR 2025
Volume | Issue number V
Pages (from-to) 459-466
Publisher Cham: Springer
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract
Decision-making and opinion-forming are everyday tasks that involve weighing pro and con arguments. The goal of Touché is to foster the development of support-technologies for decision-making and opinion-forming and to improve our understanding of these processes. This sixth edition of the lab features four shared tasks, three of which include generative systems: (1) Retrieval-Augmented Debating (RAD), in which participants submit generative retrieval systems that argue against their users and evaluate such systems (new task); (2) Ideology and Power Identification in Parliamentary Debates, in which participants identify from a speech the political leaning of the speaker’s party and whether it was governing at the time of the speech (2nd edition); (3) Image Retrieval/Generation for Arguments, in which participants find images to convey a written argument (4th edition, joint task with ImageCLEF); and (4) Advertisement in Retrieval-Augmented Generation, in which participants generate responses to queries with ads inserted and detect such inserted ads (new task). In this paper, we briefly describe the planned setup for the sixth lab edition at CLEF 2025 and summarize the results of the 2024 edition.
Document type Conference contribution
Language English
Published at https://doi.org/10.1007/978-3-031-88720-8_67
Other links https://www.scopus.com/pages/publications/105006599293
Downloads
Overview of Touché 2025 (Final published version)
Permalink to this page
Back