Lost in Variation? Evaluating NLI Performance in Basque and Spanish Geographical Variants

Jaione Bengoetxea, Itziar Gonzalez-Dios, Rodrigo Agerri

Keywords: Geographical variation, evaluation, NLI, Basque, Spanish

TL;DR: XNLIvar, a manually curated dataset for language variants of Basque and Spanish, shows a decrease in performance in encoder only and decoder based Large Language Models, showing the need for research for variation-inclusive NLP resources

Abstract: In this paper, we evaluate the capacity of current language technologies to understand Basque and Spanish language varieties. We use Natural Language Inference (NLI) as a pivot task and introduce a novel, manually-curated parallel dataset in Basque and Spanish, along with their respective variants. Our empirical analysis of crosslingual and in-context learning experiments using encoder-only and decoder-based Large Language Models (LLMs) shows a performance drop when handling linguistic variation, especially in Basque. Error analysis suggests that this decline is not due to lexical overlap, but rather to the linguistic variation itself. Further ablation experiments indicate that encoder-only models particularly struggle with Western Basque, which aligns with linguistic theory that identifies peripheral dialects (e.g., Western) as more distant from the standard. All data and code are publicly available.

Submission Number: 181