Published in the Proceedings of the First Workshop on Language Models for Low-Resource Languages (LoResLM 2025), at COLING 2025, Abu Dhabi, UAE.
The paper presents a tool that generates Arabic educational crossword puzzles from any input text using GPT-4-Turbo, GPT-3.5-Turbo and Llama3-8B-Instruct, together with Arabic-Clue-Instruct, a dataset of over 50,000 entries of text, answers, clues and categories. The model and dataset are publicly released.
Authors: Kamyar Zeinalipour, Mohamed Zaky Saad, Marco Maggini, Marco Gori.
Read the paper | Code | Models and data
All the lab's language releases are listed in Language models and datasets.