PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages

• URL: http://arxiv.org/abs/2607.05992v1
• Date: Tue, 07 Jul 2026 08:25:29 GMT
• Title: PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages
• Abstract summary: We introduce PluraMath, an extension of PolyMath to 18 additional underrepresented languages spanning 6 language families.<n>We benchmark 27 reasoning Large Language Models (LLMs) across four model scales.<n>Our analysis confirms a persistent gap in mathematical reasoning performance between high-resource and underrepresented languages.
• Score: 40.80673561512526
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating both pre-training corpora and evaluation suites. The recently released PolyMath (Wang et al., 2025) dataset represents a significant step forward, yet its coverage is still limited to 18 only high-resource languages. To address this gap, we introduce PluraMath, an extension of PolyMath to 18 additional {underrepresented languages spanning 6 language families -- ranging from mid-resource to extreme low-resource settings. We constructed the dataset through a human-curated pipeline, where native speakers thoroughly validated pre-computed translations. Using PluraMath, we then benchmark 27 reasoning LLMs across four model scales -- small, mid-size, large, and closed-source ensembles -- probing the multilingual mathematical reasoning capabilities of state-of-the-art models under diverse linguistic conditions. Our fine-grained analysis confirms a persistent gap in mathematical reasoning performance between high-resource and underrepresented languages, with stronger results largely associated with better instruction-following ability. We fully open-source our dataset, data acquisition pipeline, and evaluation framework, with the goal of lowering the barrier to multilingual benchmark development for underrepresented communities.

Related papers

• MameLoshnLM: Yiddish Language Model and Evaluation Benchmark [62.936233688546984]
  We present MameLoshnLM, the first open-source 8B- parameter language model built specifically for Yiddish.<n>Despite Yiddish's rich textual tradition, its limited digital presence and the scarcity of reliable evaluation resources have constrained progress in Yiddish language modeling.<n>Our results provide both a foundation for Yiddish NLP and a practical template for language model development in historically rich but digitally underrepresented languages.
  arXiv  Detail & Related papers  (2026-08-06T10:24:08Z)
• Crosslingual On-Policy Self-Distillation for Multilingual Reasoning [48.68444770923683]
  Crosslingual On-Policy Self-Distillation (COPSD) transfers a model's own high-resource reasoning behavior to low-resource languages.<n>Experiments on 17 low-resource African languages show that COPSD consistently improves low-resource mathematical reasoning across model sizes.
  arXiv  Detail & Related papers  (2026-05-10T14:06:09Z)
• MathMist: A Parallel Multilingual Benchmark Dataset for Mathematical Problem Solving and Reasoning [6.8892368960722346]
  We introduce MathMist, a parallel multilingual benchmark for mathematical problem solving and reasoning.<n>MathMist encompasses over 21K aligned question-answer pairs across seven languages.<n>We systematically evaluate a diverse suite of models, including open-source small and medium LLMs, proprietary systems, and multilingual-reasoning-focused models.
  arXiv  Detail & Related papers  (2025-10-16T04:59:52Z)
• Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters [53.59868121093848]
  We introduce Seed-X, a family of open-source language models (LLMs) with 7B parameter size.<n>The base model is pre-trained on a diverse, high-quality dataset encompassing both monolingual and bilingual content across 28 languages.<n>The instruct model is then finetuned to translate by Chain-of-Thought (CoT) reasoning and further enhanced through reinforcement learning (RL) to achieve better generalization across diverse language pairs.
  arXiv  Detail & Related papers  (2025-07-18T03:19:43Z)
• Scaling Test-time Compute for Low-resource Languages: Multilingual Reasoning in LLMs [3.9530780161144667]
  We investigate the multilingual mechanism by which Large Language Models internally operate in a latent space biased toward their inherently dominant language.<n>We train models to generate the chain-of-thought (CoT) in English while outputting the final response in the target language, given input in the low-resource language.<n>Our experiments demonstrate that this approach, named English-Pivoted CoT Training, outperforms other baselines, with up to 28.33% improvement.
  arXiv  Detail & Related papers  (2025-04-02T16:58:36Z)
• LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning [28.288949710191158]
  Large language models (LLMs) have exhibited impressive multilingual reasoning capabilities, driven by extensive multilingual pre-training corpora and instruction fine-tuning data.<n>A performance gap exists between high- and low-resource language reasoning tasks due to the language imbalance in the pre-training corpus.<n>We propose LinguaLIFT, a two-stage instruction tuning framework for advancing low-resource language reasoning.
  arXiv  Detail & Related papers  (2024-12-17T03:03:17Z)
• 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)
• Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations [59.056367787688146]
  This paper pioneers exploring and training powerful Multilingual Math Reasoning (xMR) LLMs. We construct the first multilingual math reasoning instruction dataset, MGSM8KInstruct, encompassing ten distinct languages. By utilizing translation, we construct the first multilingual math reasoning instruction dataset, MGSM8KInstruct, encompassing ten distinct languages.
  arXiv  Detail & Related papers  (2023-10-31T08:09:20Z)
• DN at SemEval-2023 Task 12: Low-Resource Language Text Classification via Multilingual Pretrained Language Model Fine-tuning [0.0]
  Most existing models and datasets for sentiment analysis are developed for high-resource languages, such as English and Chinese. The AfriSenti-SemEval 2023 Shared Task 12 aims to fill this gap by evaluating sentiment analysis models on low-resource African languages. We present our solution to the shared task, where we employed different multilingual XLM-R models with classification head trained on various data.
  arXiv  Detail & Related papers  (2023-05-04T07:28:45Z)

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.