Overview of PAN 2025: Voight-Kampff Generative AI Detection, Multilingual Text Detoxification, Multi-author Writing Style Analysis, and Generative Plagiarism Detection
Bevendorff, Janek Dementieva, Daryna Froebe, Maik Gipp, Bela Greiner-Petter, Andre Karlgren, Jussi Mayerl, Maximilian Nakov, Preslav Panchenko, Alexander Potthast, Martin
Bevendorff, Janek
Dementieva, Daryna
Froebe, Maik
Gipp, Bela
Greiner-Petter, Andre
Karlgren, Jussi
Mayerl, Maximilian
Nakov, Preslav
Panchenko, Alexander
Potthast, Martin
Supervisor
Department
Natural Language Processing
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The goal of the PAN lab is to advance the state of the art in text forensics and stylometry through an objective evaluation of new and established methods on new benchmark datasets. In 2025, we organized four shared tasks: (1) generative AI detection, particularly in mixed and obfuscated authorship scenarios, (2) multilingual text detoxification, a continued task that aims re-formulate text in a non-toxic way for multiple languages, and (3) multi-author writing style analysis, a continued task that aims to find positions of authorship change, and (4) generative plagiarism detection, a new task that targets source retrieval and text alignment between generated text and source documents. PAN 2025 concluded successfully with 56 notebook papers.
Citation
J. Bevendorff et al., “Overview of PAN 2025: Voight-Kampff Generative AI Detection, Multilingual Text Detoxification, Multi-author Writing Style Analysis, and Generative Plagiarism Detection,” pp. 388–411, 2026, doi: 10.1007/978-3-032-04354-2_21
Source
Experimental IR Meets Multilinguality, Multimodality, and Interaction
Conference
16th International Conference of the CLEF Association, CLEF 2025
Keywords
Subjects
Source
16th International Conference of the CLEF Association, CLEF 2025
Publisher
Springer Nature