Lingdex.org:Leveraging LLMs to Structure and Explore Linguistic Olympiad Puzzles for Learning and Teaching Linguistics

Jonathan Sakunkoo, Annabella Sakunkoo


Abstract
Linguistics Olympiad puzzles provide a valuable but underutilized resource for teaching linguistic reasoning, typology, and cross-cultural understanding. Many of these puzzles feature endangered and low-resource languages and thus offer a rare opportunity to integrate linguistic diversity into education at a time when over 40% of the world’s languages face extinction. This paper presents Lingdex, a novel web-based platform that leverages large language models (LLMs) to classify, organize, and enliven Linguistics Olympiad problems across various linguistic categories such as syntax, morphology, semantics, phonology, and language families. By applying NLP techniques to the multilingual and multicultural corpora of linguistics puzzles drawn from international and national Olympiads, Lingdex supports language and linguistics education, problem-based learning, and curriculum development. The visual, interactive platform also includes problems based on endangered and rare languages to raise awareness and interest in linguistic diversity. We present results from a user study that shows increased learner interest and appreciation for global linguistic richness.
Anthology ID:
2025.ranlp-1.121
Volume:
Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Galia Angelova, Maria Kunilovskaya, Marie Escribe, Ruslan Mitkov
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
1053–1057
Language:
URL:
https://aclanthology.org/2025.ranlp-1.121/
DOI:
Bibkey:
Cite (ACL):
Jonathan Sakunkoo and Annabella Sakunkoo. 2025. Lingdex.org:Leveraging LLMs to Structure and Explore Linguistic Olympiad Puzzles for Learning and Teaching Linguistics. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1053–1057, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Lingdex.org:Leveraging LLMs to Structure and Explore Linguistic Olympiad Puzzles for Learning and Teaching Linguistics (Sakunkoo & Sakunkoo, RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-1.121.pdf