# Desegma-IT - Detection and Segmentation of Machine Generated Text in Italian

## Call for participation

https://desegma.github.io/

Desegma-IT is a Shared Task of the 9th evaluation campaign organized by the EVALITA initiative.

Desegma-IT’s shared tasks of Detection and Segmentation aim to stress-test the robustness of machine-generated text detectors by evaluating their performance under settings where the I.I.D. (independent and identically distributed) assumption does not hold. While state-of-the-art MGT detectors have reported high accuracy, such results often stem from unrealistic experimental settings: for example, relying on prior knowledge of the text generator, or failing to consider domain shifts and efficient fine-tuning - or post-tuning - strategies.

## Tasks

* MGT Detection in the Wild * Human-Machine Text Segmentation

Check the Tasks page https://desegma.github.io/tasks/ for more details about the tasks and the dataset. We support and wish for many diverse approaches to the tasks. Any kind of submission, either based on LLMs or any other approach is welcome!

## Team Registration Register your team at this google form, to receive updates on the tasks: https://docs.google.com/forms/d/e/1FAIpQLSdAgOMmO-GK1K-w5Mn-eZQRJNTn9BQj8mQU...

## Important Dates

* Data Release: September 22nd, 2025 * Evaluation Window: November 24th - December 1st * Camera Ready Deadline: February 2nd, 2026 * Workshop Date: February 26th-27th, 2026, Bari (Italy)

## Organizers

Andrea Esuli, Andrea Pedrotti, Giovanni Puccetti ISTI-CNR