Multilingual Large Language Models do not comprehend all natural languages to equal degrees

• URL: http://arxiv.org/abs/2602.20065v1
• Date: Mon, 23 Feb 2026 17:22:46 GMT
• Title: Multilingual Large Language Models do not comprehend all natural languages to equal degrees
• Authors: Natalia Moskvina, Raquel Montero, Masaya Yoshida, Ferdy Hubers, Paolo Morosi, Walid Irhaymi, Jin Yan, Tamara Serrano, Elena Pagliarini, Fritz Günther, Evelina Leivada,
• Abstract summary: Large Language Models (LLMs) play a critical role in how humans access information.<n>Most benchmarks evaluate LLMs in languages spoken by Western, Educated, Industrialised, Rich, and Democratic (WEIRD) communities.<n>We prompt 3 popular models on a language comprehension task across 12 languages.<n>Our results suggest that the models exhibit remarkable linguistic accuracy across typologically diverse languages.
• Score: 3.1312895682585595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) play a critical role in how humans access information. While their core use relies on comprehending written requests, our understanding of this ability is currently limited, because most benchmarks evaluate LLMs in high-resource languages predominantly spoken by Western, Educated, Industrialised, Rich, and Democratic (WEIRD) communities. The default assumption is that English is the best-performing language for LLMs, while smaller, low-resource languages are linked to less reliable outputs, even in multilingual, state-of-the-art models. To track variation in the comprehension abilities of LLMs, we prompt 3 popular models on a language comprehension task across 12 languages, representing the Indo-European, Afro-Asiatic, Turkic, Sino-Tibetan, and Japonic language families. Our results suggest that the models exhibit remarkable linguistic accuracy across typologically diverse languages, yet they fall behind human baselines in all of them, albeit to different degrees. Contrary to what was expected, English is not the best-performing language, as it was systematically outperformed by several Romance languages, even lower-resource ones. We frame the results by discussing the role of several factors that drive LLM performance, such as tokenization, language distance from Spanish and English, size of training data, and data origin in high- vs. low-resource languages and WEIRD vs. non-WEIRD communities.

Related papers

• FormosanBench: Benchmarking Low-Resource Austronesian Languages in the Era of Large Language Models [1.2403152094314245]
  We introduce FORMOSANBENCH, the first benchmark for evaluating large language models (LLMs) on low-resource Austronesian languages.<n>We assess model performance in zero-shot, 10-shot, and fine-tuned settings using FORMOSANBENCH.<n>Our results reveal a substantial performance gap between high-resource and Formosan languages.
  arXiv  Detail & Related papers  (2025-06-12T07:02:28Z)
• Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? [59.970391602080205]
  Despite multilingual training, LRMs tend to default to reasoning in high-resource languages at test time.<n>Cultural reasoning degrades performance on reasoning tasks but benefits cultural tasks, while safety evaluations exhibit language-specific behavior.
  arXiv  Detail & Related papers  (2025-05-23T02:46:18Z)
• Enhancing Code Generation for Low-Resource Languages: No Silver Bullet [55.39571645315926]
  Large Language Models (LLMs) rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages.<n>For low-resource languages, the limited availability of such data hampers the models' ability to generalize effectively.<n>We present an empirical study investigating the effectiveness of several approaches for boosting LLMs' performance on low-resource languages.
  arXiv  Detail & Related papers  (2025-01-31T12:23:28Z)
• Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models [52.00446751692225]
  We present a novel and simple yet effective method called textbfDictionary textbfInsertion textbfPrompting (textbfDIP) When providing a non-English prompt, DIP looks up a word dictionary and inserts words' English counterparts into the prompt for LLMs. It then enables better translation into English and better English model thinking steps which leads to obviously better results.
  arXiv  Detail & Related papers  (2024-11-02T05:10:50Z)
• Lens: Rethinking Multilingual Enhancement for Large Language Models [70.85065197789639]
  We propose Lens, a novel approach to enhance multilingual capabilities in large language models (LLMs)<n>Lens operates on two subspaces: the language-agnostic subspace, where it aligns target languages with the central language to inherit strong semantic representations, and the language-specific subspace, where it separates target and central languages to preserve linguistic specificity.<n>Lens significantly improves multilingual performance while maintaining the model's English proficiency, achieving better results with less computational cost compared to existing post-training approaches.
  arXiv  Detail & Related papers  (2024-10-06T08:51:30Z)
• Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis [20.79017989484242]
  Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages.<n>We conduct experiments on several open-source LLM models, analyzing probing accuracy, trends across layers, and similarities between probing vectors for multiple languages.
  arXiv  Detail & Related papers  (2024-09-22T14:14:05Z)
• Towards a More Inclusive AI: Progress and Perspectives in Large Language Model Training for the Sámi Language [7.289015788793582]
  This work focuses on increasing technological participation for the S'ami language. We draw the attention of the ML community towards the language modeling problem of Ultra Low Resource (ULR) languages. We have compiled the available S'ami language resources from the web to create a clean dataset for training language models.
  arXiv  Detail & Related papers  (2024-05-09T13:54:22Z)
• Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages [48.40607157158246]
  Large Language Models (LLMs) perform better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate.<n>We propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using internal representations.<n>Our analysis reveals that high-resource languages exhibit higher similarity scores with English, demonstrating superior performance, while low-resource languages show lower similarity scores.
  arXiv  Detail & Related papers  (2024-04-17T16:53:16Z)
• Could We Have Had Better Multilingual LLMs If English Was Not the Central Language? [4.655168524016426]
  Large Language Models (LLMs) demonstrate strong machine translation capabilities on languages they are trained on. Our study delves into Llama2's translation capabilities. Our experiments show that the 7B Llama2 model yields above 10 BLEU when translating into all languages it has seen.
  arXiv  Detail & Related papers  (2024-02-21T16:32:38Z)
• Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon [78.12363425794214]
  We focus on zero-shot sentiment analysis tasks across 34 languages, including 6 high/medium-resource languages, 25 low-resource languages, and 3 code-switching datasets. We demonstrate that pretraining using multilingual lexicons, without using any sentence-level sentiment data, achieves superior zero-shot performance compared to models fine-tuned on English sentiment datasets.
  arXiv  Detail & Related papers  (2024-02-03T10:41:05Z)
• Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [75.33019401706188]
  Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. We propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English. Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages.
  arXiv  Detail & Related papers  (2023-06-20T08:27:47Z)
• Multilingual Language Model Adaptive Fine-Tuning: A Study on African Languages [19.067718464786463]
  We perform multilingual adaptive fine-tuning (MAFT) on 17 most-resourced African languages and three other high-resource languages widely spoken on the African continent. To further specialize the multilingual PLM, we removed vocabulary tokens from the embedding layer that corresponds to non-African writing scripts before MAFT. Our approach is competitive to applying LAFT on individual languages while requiring significantly less disk space.
  arXiv  Detail & Related papers  (2022-04-13T16:13:49Z)
• Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios? [15.995677143912474]
  We focus on North-African colloquial dialectal Arabic written using an extension of the Latin script, called NArabizi.<n>We show that a character-based model trained on only 99k sentences of NArabizi and fined-tuned on a small treebank leads to performance close to those obtained with the same architecture pre-trained on large multilingual and monolingual models.
  arXiv  Detail & Related papers  (2021-10-26T14:59:16Z)
• Discovering Representation Sprachbund For Multilingual Pre-Training [139.05668687865688]
  We generate language representation from multilingual pre-trained models and conduct linguistic analysis. We cluster all the target languages into multiple groups and name each group as a representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.
  arXiv  Detail & Related papers  (2021-09-01T09:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.