MiMIC 2025 : MiMIC: Multi-Modal AI Content Moderation shared task
MiMIC: Multi-Modal AI Content Moderation shared task
Event Notification Type: Call for Participation
We kindly invite you to participate at the MiMIC: Multi-Modal AI Content Moderation shared task organized under the Iberian Language Evaluation Forum (IberLEF) 2025 which will be held in Zaragoza (Spain) on September 2025.
This shared task focuses on the problem of detecting whether a text-image pair is partially or completely generated by generative models like GPT, Stable Diffusion, and others. We hope to understand whether multi-modal framing can improve the performance of generated content detectors.
MiMIC consists of two subtasks focused on the same detection task, both for English and Spanish. Both subtasks involve multiclass classification of (text, image) pairs into four categories: fully-generated, fully-human, image-generated, and text-generated.
- Subtask 1: Multimodal Machine Generated Content Detection in English.
- Subtask 2: Multimodal Machine Generated Content Detection in Spanish.
This shared task is open to everyone! We do not constrain the target community allowing participation from students to companies.
Important Links
Task Website: https://sites.google.com/view/mimic-2025/home?authuser=0
Key Dates (All deadlines are at 23:59 AoE)
- Training Phase Begins (Training Data Released): March 1, 2025
- Test Phase Begins (Test Data Released): May 1, 2025
- Submission Deadline for Participants' Runs (hard deadline): May 23, 2025
- Results Notification & Ranking Release: May 27, 2025
- Submission Deadline for Participants' Working Notes (hard deadline): June 13, 2025
- Camera-Ready Submission Deadline (hard deadline): June 27, 2025
Task organizers
- José Ángel González (Symanto)
- Areg Sarvazyan (Symanto)
- Angelo Basile (Symanto)
- Ian Borrego (Symanto)
- Mara Chinea (Symanto)
- Francisco Rangel (Symanto)
Please reach out to the organizers at [email protected], or join the Google group (https://groups.google.com/g/mimic-shared-task) to connect with the other participants and organizers.
We look forward to your participation and can’t wait to see the innovative solutions you come up with! If you have any questions, feel free to reach out.
Let’s work together to tackle this important challenge!
Event Notification Type: Call for Participation
We kindly invite you to participate at the MiMIC: Multi-Modal AI Content Moderation shared task organized under the Iberian Language Evaluation Forum (IberLEF) 2025 which will be held in Zaragoza (Spain) on September 2025.
This shared task focuses on the problem of detecting whether a text-image pair is partially or completely generated by generative models like GPT, Stable Diffusion, and others. We hope to understand whether multi-modal framing can improve the performance of generated content detectors.
MiMIC consists of two subtasks focused on the same detection task, both for English and Spanish. Both subtasks involve multiclass classification of (text, image) pairs into four categories: fully-generated, fully-human, image-generated, and text-generated.
- Subtask 1: Multimodal Machine Generated Content Detection in English.
- Subtask 2: Multimodal Machine Generated Content Detection in Spanish.
This shared task is open to everyone! We do not constrain the target community allowing participation from students to companies.
Important Links
Task Website: https://sites.google.com/view/mimic-2025/home?authuser=0
Key Dates (All deadlines are at 23:59 AoE)
- Training Phase Begins (Training Data Released): March 1, 2025
- Test Phase Begins (Test Data Released): May 1, 2025
- Submission Deadline for Participants' Runs (hard deadline): May 23, 2025
- Results Notification & Ranking Release: May 27, 2025
- Submission Deadline for Participants' Working Notes (hard deadline): June 13, 2025
- Camera-Ready Submission Deadline (hard deadline): June 27, 2025
Task organizers
- José Ángel González (Symanto)
- Areg Sarvazyan (Symanto)
- Angelo Basile (Symanto)
- Ian Borrego (Symanto)
- Mara Chinea (Symanto)
- Francisco Rangel (Symanto)
Please reach out to the organizers at [email protected], or join the Google group (https://groups.google.com/g/mimic-shared-task) to connect with the other participants and organizers.
We look forward to your participation and can’t wait to see the innovative solutions you come up with! If you have any questions, feel free to reach out.
Let’s work together to tackle this important challenge!