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

2026-02-09

AI Summary

This work addresses the challenges posed by generative AI—such as text authenticity, authorship attribution, plagiarism, and secure reasoning—by advancing textual forensics through five core tasks: detection of AI-generated text, robustness evaluation of text watermarking, multi-author style analysis, detection of generative plagiarism, and provenance tracing and security assessment of reasoning trajectories. Notably, it introduces text watermarking and reasoning trajectory analysis as novel forensic tasks, thereby expanding the boundaries of generated content verification. The framework significantly enhances the identification of AI-generated text in mixed and obfuscated scenarios. Built upon the TIRA platform with Dockerized submissions to ensure reproducibility, the initiative has attracted over 1,100 experimental submissions since 2012, fostering standardization and technological progress in textual forensics.

Technology Category

• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

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.

Problem

• Generative AI Detection
• Text Watermarking
• Multi-author Writing Style Analysis
• Generative Plagiarism Detection
• Reasoning Trajectory Detection

Innovation

• Text Watermarking
• Reasoning Trajectory Detection
• Generative AI Detection
• Generative Plagiarism Detection
• Computational Stylometry