Do Large Language Models Grasp the Grammar? Evidence from Grammar-Book-Guided Probing in Luxembourgish

Lujun LI, Yewei Song, Lama Sleem, Yiqun Wang, Yangjie Xu, Cedric LOTHRITZ, Niccolo' Gentile, Radu State, Tegawendé F. Bissyandé, Jacques Klein


Abstract
Grammar refers to the system of rules that governs the structural organization and the semantic relations among linguistic units such as sentences, phrases, and words within a given language. In natural language processing, there remains a notable scarcity of grammar-focused evaluation protocols, a gap that is even more pronounced for low-resource languages. Moreover, the extent to which large language models genuinely comprehend grammatical structure, especially the mapping between syntactic structures and meanings remains under debate. To investigate this issue, we propose a Grammar-Book–Guided evaluation pipeline intended to provide a systematic and generalizable framework for grammar evaluation consisting of four key stages, and in this work we take Luxembourgish as a case study. The results show a weak positive correlation between translation performance and grammatical understanding, indicating that strong translations do not necessarily imply deep grammatical competence. Larger models perform well overall due to their semantic strength but remain weak in morphology and syntax, struggling particularly with Minimal Pair tasks, while strong reasoning ability offers a promising way to enhance their grammatical understanding.
Anthology ID:
2026.lrec-main.904
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
11552–11561
Language:
URL:
https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.904/
DOI:
Bibkey:
Cite (ACL):
Lujun LI, Yewei Song, Lama Sleem, Yiqun Wang, Yangjie Xu, Cedric LOTHRITZ, Niccolo' Gentile, Radu State, Tegawendé F. Bissyandé, and Jacques Klein. 2026. Do Large Language Models Grasp the Grammar? Evidence from Grammar-Book-Guided Probing in Luxembourgish. International Conference on Language Resources and Evaluation, main:11552–11561.
Cite (Informal):
Do Large Language Models Grasp the Grammar? Evidence from Grammar-Book-Guided Probing in Luxembourgish (LI et al., LREC 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.904.pdf