This work reports the first systematic and large-scale evaluation of LLMs in Kyrgyz using the KyrgyzLLM-Bench benchmark suite, evaluating 26 open- and closed-source LLMs under zero-shot and few-shot settings, and analyzing model performance, cross-lingual transfer, and the impact of translation artifacts on evaluation reliability.
Abstract
Evaluating large language models (LLMs) across languages remains challenging, as most multilingual benchmarks rely on translated English datasets, often obscuring linguistic and cultural specificity in the target language. This issue is particularly pronounced for less-resourced languages such as Kyrgyz, where reliable natively authored evaluation data are scarce. Building on previously introduced Kyrgyz-language evaluation datasets, this work reports the first systematic and large-scale evaluation of LLMs in Kyrgyz using the KyrgyzLLM-Bench benchmark suite. KyrgyzLLM-Bench comprises two natively authored datasets$-$KyrgyzMMLU and KyrgyzRC$-$together with carefully translated and manually post-edited versions of WinoGrande, HellaSwag, BoolQ, and TruthfulQA. We evaluate 26 open- and closed-source LLMs under zero-shot and few-shot settings, analyzing model performance, cross-lingual transfer, and the impact of translation artifacts on evaluation reliability. Across families and tasks, model rankings transfer broadly from English to Kyrgyz on WinoGrande and BoolQ, and to a lesser extent on MMLU, while HellaSwag exhibits a substantial English-Kyrgyz performance gap consistent with translation-induced plausibility shifts. Few-shot prompting improves several open-source models on reading comprehension but behaves inconsistently for proprietary models on translated tasks. We publicly release all datasets, evaluation code, and per-model results, and integrate the Kyrgyz tasks into a widely used multilingual evaluation framework to support future research on Kyrgyz NLP.
Large language models (LLMs) have achieved remarkable success in high-resource languages, yet their performance on Traditional Mongolian remains highly limited. A primary bottleneck is the absence of a systematic evaluation framework, which precludes quantitative comparison and obscures directions for model optimization. In this paper, we introduce TM-Bench, the first comprehensive benchmark for LLMs on Traditional Mongolian. TM-Bench adopts a hybrid construction strategy consisting of human-verified Translation-based Adaptation, Expert-Original Authoring, and Semi-automated Synthesis. It comprises 18,357 instances spanning five tasks across both natural language understanding and generation to evaluate models' reasoning, knowledge application, and linguistic proficiency. We conduct systematic evaluations across representative model families. The results show that on understanding tasks, model performance lags significantly behind high-resource languages, with only a few models performing slightly above the random baseline. For generation tasks, both automatic metrics and double-blind human evaluations reveal severe semantic collapse, failing to generate coherent text and often producing unreadable gibberish. These findings underscore the critical role of TM-Bench as a foundational infrastructure for evaluating LLMs in Traditional Mongolian and catalyzing future model optimization. Our benchmark and code are available at https://github.com/gao1948083886/TM-Bench.
Zhenjie Gao, Feilong Bao, Aruukhan Bai et al.· Annual International ACM SIG...· 0 citations
MameLoshnLM, the first open-source 8B-parameter language model built specifically for Yiddish, is presented, providing both a foundation for Yiddish NLP and a practical template for language model development in historically rich but digitally underrepresented languages.
Uri Katz, Omer Goldman, Tomasz Limisiewicz et al.· 0 citations
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.
Daryna Dementieva, N. Babakov, Kathy Hammerl et al.· 0 citations
Existing safety evaluation datasets for large language models (LLMs) predominantly focus on English and Western contexts, often overlooking the linguistic diversity and culturally grounded safety risks present in other languages. To address this gap, we introduce SurakshaEval, a novel safety benchmark composed of human-written prompts spanning real-world scenarios, explicitly designed for ten major Indian languages - Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Punjabi, Tamil, and Telugu, along with English. SurakshaEval includes both generic prompts common across India and region- and language-specific prompts that capture localized sociocultural sensitivities. We benchmark a broad range of state-of-the-art LLMs on SurakshaEval, establish baseline safety performance, and identify recurring failure modes, including over-refusal, missed detection of implicit bias, and insufficient contextual awareness in regionally sensitive settings. Our results show that even strong multilingual LLMs struggle to reliably meet nuanced safety requirements when operating in Indic languages, particularly in native scripts. These findings highlight the urgent need for safety evaluation frameworks that incorporate region-specific data and structured assessment protocols, enabling the development and deployment of AI systems that operate securely, ethically, and in alignment with diverse societal values. Our code and data are available at https://github.com/debobanerjee/SurakshaEval. Warning: This paper contains text that may be offensive or unsafe.
Debopriyo Banerjee, K. R. Kavitha, Angana Borah et al.· 0 citations
Neural machine translation (NMT) systems are widely used, but their performance remains strongly dependent on the availability of large-scale digital corpora, making translation for low-resource languages a persistent challenge. In parallel, large language models (LLMs) have recently emerged as a promising paradigm for multilingual text generation and translation; however, their behavior in low-resource settings remains largely underexplored. The challenge becomes even more acute for historical languages. Chagatai, a historical Turkic literary language of Central Asia with no native speakers, unstable orthography, and parallel data, represents an extreme case of such a condition. This study investigates whether transliteration significantly affects translation performance and how LLM-based and NMT-based systems compare under an extremely low-resource setting. To address these questions, we evaluated four source-text configurations (original Arabic script, expert manual transliteration, LLM-based transliteration, and rule-based Uroman transliteration) for translation into six target languages: Kazakh, English, Uzbek, Uyghur, Turkish, Russian, and Arabic. The results show that manual transliteration consistently yields the best translation performance, while noisy automatic romanization reduces these gains. For model comparison, GPT-4o was assessed alongside two fine-tuned NMT baselines, NLLB and TranslateGemma. The findings further show that LLM-based translation can be competitive with, and in some settings outperform, fine-tuned NMT systems, although this advantage comes with lower interpretability. Overall, these findings show that, for extremely low-resource historical languages written in non-Latin scripts, source-side representation is a decisive factor and may be as important as the choice of translation model itself.
A. Mansurova, Meruert Bekmukhamedova, Bekarys Baibolat et al.· Electronics· 0 citations
We present L3Cube-IndicQuest v2, a large-scale gold-standard multilingual question-answering benchmark for evaluating the India-specific factual knowledge of Large Language Models (LLMs). The benchmark comprises 3,471 curriculum-grounded English question--answer pairs spanning nine domains, curated from educational curricula, competitive examination materials, and domain-specific reference books. We introduce a practical hybrid construction strategy that combines context-grounded LLM-based question generation and validation with semantic deduplication and human verification, enabling scalable creation of benchmark data while preserving annotation quality. The benchmark is translated into 19 Indic languages, yielding a publicly released multilingual dataset of 69,420 question--answer pairs across 20 languages. We evaluate six LLMs under three protocols: LLM-as-a-judge and two deterministic lexical criteria, exact-substring and word-overlap matching. All three produce almost the same model ranking, showing that the results do not depend on the choice of judge. The frontier commercial model leads by a wide margin, and among open-weight models Gemma4 31B outperforms the Indic-specialised Sarvam 30B in every evaluated Indic language.
Rinit Jain, Tirthraj Mahajan, Advait Joshi et al.· 0 citations