The First Shared Task on Fine-Tuning LLMs for Ukrainian
The Third UNLP organizes the first Shared Task on Fine-Tuning Large Language Models (LLMs) for Ukrainian.
Important Dates
January 15, 2024 — Shared task announcement
February 12, 2024 — Second call for participation; release of train data
February 16, 2024 — Release of test data to registered participants
February 24, 2024 — Registration deadline; release of open questions
February 26, 2024 — Submission of system responses
March 4, 2024 — Results of the Shared Task announced
March 6, 2024 — Shared Task paper due
March 27, 2024 — Notification of acceptance
April 5, 2024 — Camera-ready papers due
May 25, 2024 — 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.
Join the discussions in Discord via https://discord.gg/kCc6xgWbCJ.
Publication
Participants in the shared task are invited to submit a paper to the UNLP 2024 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 2024 specially dedicated to the Shared Task.
Link for paper submission: https://softconf.com/lrec-coling2024/unlp2024/