Scholarlink

The goal of the PAN workshop is to advance computational stylometry and text forensics via objective and reproducible evaluation. In 2026, we run the following five tasks: (1)  Voight-Kampff Generative AI Detection, particularly in mixed and obfuscated authorship scenarios, (2)  Text Watermarking, a new task that aims to find new and benchmark the robustness of existing text watermarking schemes, (3)  Multi-author Writing Style Analysis, a continued task that aims to find positions of authorship change, (4)  Generative Plagiarism Detection, a continued task that targets source retrieval and text alignment between generated text and source documents, and (5)  Reasoning Trajectory Detection, a new task that deals with source detection and safety detection of LLM-generated or human-written reasoning trajectories. As in previous years, PAN invites software submissions as easy-to-reproduce Docker containers for most of the tasks. Since PAN 2012, more than 1,100 submissions have been made this way via the TIRA experimentation platform [8].

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Overview of PAN 2026: Voight-Kampff Generative AI Detection, Text Watermarking, Multi-author Writing Style Analysis, Generative Plagiarism Detection, and Reasoning Trajectory Detection

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Janek Bevendorff,
  • Maik Fröbe,
  • André Greiner-Petter,
  • Andreas Jakoby,
  • Maximilian Mayerl,
  • Preslav Nakov,
  • Henry Plutz,
  • Martin Potthast,
  • Benno Stein,
  • Minh Ngoc Ta,
  • Yuxia Wang,
  • Eva Zangerle

摘要

The goal of the PAN workshop is to advance computational stylometry and text forensics via objective and reproducible evaluation. In 2026, we run the following five tasks: (1)  Voight-Kampff Generative AI Detection, particularly in mixed and obfuscated authorship scenarios, (2)  Text Watermarking, a new task that aims to find new and benchmark the robustness of existing text watermarking schemes, (3)  Multi-author Writing Style Analysis, a continued task that aims to find positions of authorship change, (4)  Generative Plagiarism Detection, a continued task that targets source retrieval and text alignment between generated text and source documents, and (5)  Reasoning Trajectory Detection, a new task that deals with source detection and safety detection of LLM-generated or human-written reasoning trajectories. As in previous years, PAN invites software submissions as easy-to-reproduce Docker containers for most of the tasks. Since PAN 2012, more than 1,100 submissions have been made this way via the TIRA experimentation platform [8].