LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Aji, Alham Fikri, Cohn, Trevor
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909739908071424
author Aji, Alham Fikri
Cohn, Trevor
author_facet Aji, Alham Fikri
Cohn, Trevor
contents As one of the world's most populous countries, with 700 languages spoken, Indonesia is behind in terms of NLP progress. We introduce LoraxBench, a benchmark that focuses on low-resource languages of Indonesia and covers 6 diverse tasks: reading comprehension, open-domain QA, language inference, causal reasoning, translation, and cultural QA. Our dataset covers 20 languages, with the addition of two formality registers for three languages. We evaluate a diverse set of multilingual and region-focused LLMs and found that this benchmark is challenging. We note a visible discrepancy between performance in Indonesian and other languages, especially the low-resource ones. There is no clear lead when using a region-specific model as opposed to the general multilingual model. Lastly, we show that a change in register affects model performance, especially with registers not commonly found in social media, such as high-level politeness `Krama' Javanese.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12459
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages
Aji, Alham Fikri
Cohn, Trevor
Computation and Language
As one of the world's most populous countries, with 700 languages spoken, Indonesia is behind in terms of NLP progress. We introduce LoraxBench, a benchmark that focuses on low-resource languages of Indonesia and covers 6 diverse tasks: reading comprehension, open-domain QA, language inference, causal reasoning, translation, and cultural QA. Our dataset covers 20 languages, with the addition of two formality registers for three languages. We evaluate a diverse set of multilingual and region-focused LLMs and found that this benchmark is challenging. We note a visible discrepancy between performance in Indonesian and other languages, especially the low-resource ones. There is no clear lead when using a region-specific model as opposed to the general multilingual model. Lastly, we show that a change in register affects model performance, especially with registers not commonly found in social media, such as high-level politeness `Krama' Javanese.
title LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages
topic Computation and Language
url https://arxiv.org/abs/2508.12459