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

TL;DR

PAN 2026 targets rigorous, reproducible evaluation across five tasks focused on AI-generated text detection, watermarking, multi-author style change detection, generative plagiarism, and reasoning trajectory safety. It extends prior PAN work with new tasks, maintains docker-based submissions via the TIRA platform, and emphasizes robust evaluation against obfuscation and real-world data sources. The suite combines detection robustness, watermark authentication, and reasoning transparency to address practical challenges in trustworthy text analytics. The proposed datasets and evaluation plans aim to broaden domain and language coverage while guiding future improvements in robustness and safety.

Abstract

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.