UNVEILING: What Makes Linguistics Olympiad Puzzles Tricky for LLMs?

Mukund Choudhary, KV Aditya Srivatsa, Gaurja Aeron, Antara Raaghavi Bhattacharya, Dang Khoa Dang Dinh, Ikhlasul Akmal Hanif, Daria Kotova, Ekaterina Kochmar, Monojit Choudhury

Keywords: linguistic reasoning, metalinguistics, LLM evaluation, morphology, linguistics olympiad, interpretability, low resource languages, annotation

TL;DR: The study presents a linguistic features-based annotation of Linguistics Olympiad puzzles to find LLM weaknesses; LLMs are bad at puzzles with higher morphological complexity, dissimilar to English, and when the puzzle is data constrained.

Abstract: Large language models (LLMs) have demonstrated potential in reasoning tasks, but their performance on linguistics puzzles remains consistently poor. These puzzles, often derived from Linguistics Olympiad (LO) contests, provide a minimal contamination environment to assess LLMs' linguistic reasoning abilities across low-resource languages. This work analyses LLMs' performance on 629 problems across 41 low-resource languages by labelling each with linguistically informed features to unveil weaknesses. Our analyses show that LLMs struggle with puzzles involving higher morphological complexity and perform better on puzzles involving linguistic features that are also found in English. We also show that splitting words into morphemes as a pre-processing step improves solvability, indicating a need for more informed and language-specific tokenisers. These findings thus offer insights into some challenges in linguistic reasoning and modelling of low-resource languages.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 604