Shared Task on Detecting Social Media Manipulation
This Shared Task aims to challenge and assess AI capabilities to detect and classify manipulation, laying the groundwork for progress in cybersecurity and the identification of disinformation within the context of Ukrainian.
Organized jointly with Texty.org.ua, the task will be based on 9,500 Telegram posts manually annotated for ten manipulation techniques by media experts. The shared task will have two tracks: techniques classification and detection of manipulative text spans.
You can find the detailed instructions, limitations, baseline, and evaluation sample at [GitHub repository – TBD].
Important Dates
December 1, 2024 — Shared task announcement
March 23, 2025 — Registration deadline
March 24, 2025 — Release of test data to registered participants
March 31, 2025 — Submission of system responses
April 4, 2025 — Results of the Shared Task announced
April 14, 2025 — Shared Task paper due
May 12, 2025 — Notification of acceptance
June 2, 2025 — Camera-ready Shared Task papers due
July 31 or August 1, 2025 — Workshop
Task Description
This Shared Task aims to challenge and assess LLMs’ capabilities to understand and generate Ukrainian, paving the way for LLM development in Slavic languages.
In this shared task, your goal is to instruction-tune a large language model that can answer questions and perform tasks in Ukrainian. The model should possess knowledge of Ukrainian history, language, and literature, as well as common knowledge, and should be capable of generating fluent and factually accurate responses.
You can find the detailed instructions, limitations, baseline, and evaluation sample at https://github.com/unlp-workshop/unlp-2024-shared-task.
Registration
Teams that intend to participate should register by filling in [this form – TBD].
Publication
Participants in the shared task are invited to submit a paper to the UNLP 2025 workshop. Submitting a paper is not mandatory for participating in the Shared Task. Papers must follow the workshop submission instructions and will undergo regular peer review. Their acceptance will not depend on the results obtained in the shared task, but on the quality of the paper. Accepted papers will appear in the ACL anthology and will be presented at a session of UNLP 2025 specially dedicated to the Shared Task.
Link for paper submission: TBD