Low-Resource Language Processing

Ask about this topic

Overview

Low-resource language processing studies how to build reliable text, speech, and multimodal tools when data, annotation, computing resources, or standard writing conventions are limited. Common approaches include transferring multilingual pretrained models, adapting them with continued pretraining or parameter-efficient fine-tuning, creating synthetic data, and developing language-specific tokenizers, corpora, and tools. Benchmarks for tasks such as translation, speech recognition, information retrieval, reasoning, and cultural understanding increasingly test performance across languages, dialects, scripts, and domains. A central tension is that transfer and synthetic data can reduce development costs, but gains are uneven and depend on data quality, linguistic fit, and evaluation grounded in the language community.

Latest papers

CardsList

567 papers53 papers in the last four weeks, level with the four weeks before. 0.3% of all new papers.

Mar 22, 2026

Efficient Fine-Tuning Methods for Portuguese Question Answering: A Comparative Study of PEFT on BERTimbau and Exploratory Evaluation of Generative LLMs

Although large language models have transformed natural language processing, their computational costs create accessibility barriers for low-resource languages such as Brazilian Portuguese. This work presents a systematic evaluation of Parameter-Efficient Fine-Tuning (PEFT) and quantization techniques applied to BERTimbau for Question Answering on SQuAD-BR, the Brazilian Portuguese translation of SQuAD v1. We evaluate 40 configurations combining four PEFT methods (LoRA, DoRA, QLoRA, QDoRA) across two model sizes (Base: 110M, Large: 335M parameters). Our findings reveal three critical insights: (1) LoRA achieves 95.8% of baseline performance on BERTimbau-Large while reducing training time by 73.5% (F1=81.32 vs 84.86); (2) higher learning rates (2e-4) substantially improve PEFT performance, with F1 gains of up to +19.71 points over standard rates; and (3) larger models show twice the quantization resilience (loss of 4.83 vs 9.56 F1 points). These results demonstrate that encoder-based models can be efficiently fine-tuned for extractive Brazilian Portuguese QA with substantially lower computational cost than large generative LLMs, promoting more sustainable approaches aligned with Green AI principles. An exploratory evaluation of Tucano and Sabiá on the same extractive QA benchmark shows that while generative models can reach competitive F1 scores with LoRA fine-tuning, they require up to 4.2×\times more GPU memory and 3×\times more training time than BERTimbau-Base, reinforcing the efficiency advantage of smaller encoder-based architectures for this task.

Mariela M. Nina, Caio Veloso Costa, Lilian Berton +1

Institute of Science and Technology, Federal University of São Paulo (UNIFESP), São José dos Campos, SP, Brazil

Parameter-Efficient Fine-TuningQuestion AnsweringPortuguese Language ModelsLow-Resource Language ProcessingNeural Network Quantization
AskPDF
Mar 22, 2026

Benchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIF

Large language models (LLMs) frequently exhibit performance biases against regional dialects of low-resource languages. However, frameworks to quantify these disparities remain scarce. We propose a two-phase framework to evaluate dialectal bias, operationalized as comprehension degradation relative to standard Bengali, in LLM question-answering across nine Bengali dialects. First, we translate and gold-label standard Bengali questions into dialectal variants adopting a retrieval-augmented generation (RAG) pipeline to prepare 4,000 question sets. Since traditional translation quality evaluation metrics fail on unstandardized dialects, we evaluate fidelity using an LLM-as-a-judge, which human correlation confirms outperforms legacy metrics. Second, we benchmark 19 LLMs across these gold-labeled sets, running 68,395 RLAIF evaluations validated through multi-judge agreement and human fallback. Our findings reveal severe performance drops linked to linguistic divergence. For instance, responses to the highly divergent Chittagong dialect score 5.44/10, compared to 7.68/10 for Tangail. Furthermore, increased model scale does not consistently mitigate this bias. We contribute a validated translation quality evaluation method, a rigorous benchmark dataset, and a Critical Bias Sensitivity (CBS) metric for safety-critical applications.

K. M. Jubair Sami, Dipto Sumit, Ariyan Hossain +1

Department of Computer Science and Engineering BRAC University, Dhaka, Bangladesh

Social Bias in Language ModelsDialect Bias in Language ModelsLanguage Model Bias EvaluationLow-Resource Language Processing
AskPDF
Mar 22, 2026

ViCLSR: A Supervised Contrastive Learning Framework with Natural Language Inference for Natural Language Understanding Tasks

High-quality text representations are crucial for natural language understanding (NLU), but low-resource languages like Vietnamese face challenges due to limited annotated data. While pre-trained models like PhoBERT and CafeBERT perform well, their effectiveness is constrained by data scarcity. Contrastive learning (CL) has recently emerged as a promising approach for improving sentence representations, enabling models to effectively distinguish between semantically similar and dissimilar sentences. We propose ViCLSR (Vietnamese Contrastive Learning for Sentence Representations), a novel supervised contrastive learning framework specifically designed to optimize sentence embeddings for Vietnamese, leveraging existing natural language inference (NLI) datasets. Additionally, we propose a process to adapt existing Vietnamese datasets for supervised learning, ensuring compatibility with CL methods. Our experiments demonstrate that ViCLSR significantly outperforms the powerful monolingual pre-trained model PhoBERT on five benchmark NLU datasets such as ViNLI (+6.97% F1), ViWikiFC (+4.97% F1), ViFactCheck (+9.02% F1), UIT-ViCTSD (+5.36% F1), and ViMMRC2.0 (+4.33% Accuracy). ViCLSR shows that supervised contrastive learning can effectively address resource limitations in Vietnamese NLU tasks and improve sentence representation learning for low-resource languages. Furthermore, we conduct an in-depth analysis of the experimental results to uncover the factors contributing to the superior performance of contrastive learning models. ViCLSR is released for research purposes in advancing natural language processing tasks.

Tin Van Huynh, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen

University of Information Technology, Ho Chi Minh City, Vietnam. · Vietnam National University, Ho Chi Minh City, Vietnam.

Sentence EmbeddingsSupervised Contrastive LearningLow-Resource Language Processing
AskPDF
Mar 22, 2026

Left Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models

We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning, technical, and culturally grounded categories, we evaluate 2,000 responses on accuracy, fluency, and completeness. We find a consistent performance gap of 13.8-16.7 percentage points between English and low-resource language conditions, with models maintaining surface-level fluency while producing significantly less accurate content. Cross-lingual transfer-prompting models to reason in English before translating back-yields selective gains for bilingual architectures (+2.2pp to +4.3pp) but provides no benefit to English-dominant models. Our results demonstrate that current LLMs systematically underserve low-resource language communities, and that effective mitigation strategies are architecture-dependent rather than universal.

Abdul-Salem Beibitkhan

North American University

Low-Resource Language ProcessingMultilingual Language Model EvaluationCross-Lingual TransferLLM Prompting
AskPDF
Mar 21, 2026

SozKZ: Training Efficient Small Language Models for Kazakh from Scratch

Kazakh, a Turkic language spoken by over 22 million people, remains underserved by existing multilingual language models, which allocate minimal capacity to low-resource languages and employ tokenizers ill-suited to agglutinative morphology. We present SozKZ, a family of Llama-architecture language models (50M-600M parameters) trained entirely from scratch on 9 billion tokens of Kazakh text with a dedicated 50K BPE tokenizer. We evaluate all models on three Kazakh benchmarks -- multiple-choice cultural QA, reading comprehension (Belebele), and topic classification (SIB-200) -- alongside five multilingual baselines ranging from 500M to 3B parameters. Our 600M model achieves 30.3% accuracy on Kazakh cultural QA, approaching the 32.0% of Llama-3.2-1B (2x larger), and 25.5% on SIB-200 topic classification, surpassing all evaluated multilingual models up to 2B parameters. We observe consistent scaling from 50M to 600M, with MC QA accuracy rising from 22.8% to 30.3%, suggesting that further scaling remains beneficial. These results demonstrate that small, dedicated models trained from scratch with a language-appropriate tokenizer offer a viable path for low-resource language technology, achieving competitive performance at a fraction of the computational cost. All models and the tokenizer are released under open licenses.

Saken Tukenov

Independent Researcher

Language Model PretrainingSmall Language ModelsLow-Resource Language ProcessingEfficient Language Model Training
AskPDF
Mar 21, 2026

MzansiText and MzansiLM: An Open Corpus and Decoder-Only Language Model for South African Languages

Decoder-only language models can be adapted to diverse tasks through instruction finetuning, but the extent to which this generalizes at small scale for low-resource languages remains unclear. We focus on the languages of South Africa, where we are not aware of a publicly available decoder-only model that explicitly targets all eleven official written languages, nine of which are low-resource. We introduce MzansiText, a curated multilingual pretraining corpus with a reproducible filtering pipeline, and MzansiLM, a 125M-parameter language model trained from scratch. We evaluate MzansiLM on natural language understanding and generation using three adaptation regimes: monolingual task-specific finetuning, multilingual task-specific finetuning, and general multi-task instruction finetuning. Monolingual task-specific finetuning achieves strong performance on data-to-text generation, reaching 20.65 BLEU on isiXhosa and competing with encoder-decoder baselines over ten times larger. Multilingual task-specific finetuning benefits closely related languages on topic classification, achieving 78.5% macro-F1 on isiXhosa news classification. While MzansiLM adapts effectively to supervised NLU and NLG tasks, few-shot reasoning remains challenging at this model size, with performance near chance even for much larger decoder-only models. We release MzansiText and MzansiLM to provide a reproducible decoder-only baseline and clear guidance on adaptation strategies for South African languages at small scale.

Anri Lombard, Simbarashe Mawere, Temi Aina +5

University of Cape Town, Cape Town, South Africa

African Language ProcessingMultilingual Language ModelsLow-Resource Language ProcessingDecoder-Only Language ModelsLanguage Model PretrainingLLM Fine-Tuning+1
AskPDF
Mar 20, 2026

Curation of a Palaeohispanic Dataset for Machine Learning

Palaeohispanic languages are those spoken in the Iberian Peninsula before the arrival of the Romans in the 3rd Century B.C. Their study was really put on motion after Gómez Moreno deciphered the Iberian Levantine script, one of the several semi-sillabaries used by these languages. Still, the Palaeohispanic languages have varying degrees of decipherment, and none is fully known to this day. Most of the studies have been performed from a purely linguistic point of view, and a computational approach may benefit this research area greatly. However, the resources are limited and presented in an unsuitable format for techniques such as Machine Learning. Therefore, a structured dataset is constructed, which will hopefully allow more progress in the field.

Gonzalo Martínez-Fernández, Jose F Quesada, Agustín Riscos-Núñez +1

Department of Computer Science and Artificial Intelligence, Universidad de Sevilla, Avda. Reina Mercedes s/n, 41012 Seville, Spain · Department of Spanish Language, Linguistics and Theory of Literature, University of Seville, C/ Palos de la Frontera s/n 41004, Seville, Spain

Low-Resource Language Processing
AskPDF
Mar 19, 2026

What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?

We present MultiTempBench, a multilingual temporal reasoning benchmark spanning three tasks, date arithmetic, time zone conversion, and temporal relation extraction across five languages (English, German, Chinese, Arabic, and Hausa) and multiple calendar conventions (Gregorian, Hijri, and Chinese Lunar). MultiTempBench contains 15,00015,000 examples built by translating 750750 curated English questions and expanding each into controlled date-format variants. We evaluate 20 LLMs and introduce the multilingual Date Fragmentation Ratio (mDFR), calibrated with human severity ratings, together with geometric-probing analyses of internal temporal representations. We find tokenisation quality of temporal artefacts is a resource-dependent bottleneck: in low-resource languages and rarer calendar formats, fragmentation disrupts Year/Month/Day separation and accuracy collapses, while high-resource settings are often robust to digit-level splitting. Beyond tokenisation, crossed mixed-effects regression shows that temporal linearity is the strongest predictor of temporal reasoning in high-resource languages, whereas fragmentation is the stronger predictor in low-resource languages. Code is available at: https://github.com/gagan3012/mtb

Gagan Bhatia, Ahmad Muhammad Isa, Maxime Peyrard +1

University of Aberdeen · Université Grenoble Alpes & CNRS

Tokenization in Language ModelsTemporal Reasoning in Language ModelsLanguage ModelingMultilingual Language Model EvaluationLow-Resource Language Processing
AskPDF
Mar 19, 2026

DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units

We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to span a wide range of phonemic contrasts. Given only 10 hours of speech in a previously unseen language, systems must produce discrete units that are mapped to a predefined phoneme inventory, through either a many-to-one or a one-to-one assignment. The resulting sequences are evaluated for unit quality, recognition and segmentation. We provide four pretrained multilingual HuBERT and SpidR baselines, and show that phonemic information is available enough in current models for derived units to correlate well with phonemes, though with variations across languages.

Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo +3

LSCP, ENS, EHESS, CNRS, PSL University, France · University of Toronto, Canada

Speech ProcessingSelf-Supervised Speech Representation LearningLow-Resource Language ProcessingDiscrete Speech Representation Learning
AskPDF
Mar 18, 2026

CWoMP: Morpheme Representation Learning for Interlinear Glossing

Interlinear glossed text (IGT) is a standard notation for language documentation which is linguistically rich but laborious to produce manually. Recent automated IGT methods treat glosses as character sequences, neglecting their compositional structure. We propose CWoMP (Contrastive Word-Morpheme Pretraining), which instead treats morphemes as atomic form-meaning units with learned representations. A contrastively trained encoder aligns words-in-context with their constituent morphemes in a shared embedding space; an autoregressive decoder then generates the morpheme sequence by retrieving entries from a mutable lexicon of these embeddings. Predictions are interpretable--grounded in lexicon entries--and users can improve results at inference time by expanding the lexicon without retraining. We evaluate on diverse low-resource languages, showing that CWoMP outperforms existing methods while being significantly more efficient, with particularly strong gains in extremely low-resource settings.

Morris Alper, Enora Rice, Bhargav Shandilya +2

Carnegie Mellon University · University of Colorado Boulder

Representation LearningLow-Resource Language Processing
AskPDF
Mar 18, 2026

Toward Generalized Cross-Lingual Hateful Language Detection with Web-Scale Data and Ensemble LLM Annotations

We study whether large-scale unlabelled web data and LLM-based synthetic annotations can improve multilingual hate speech detection. Starting from texts crawled via OpenWebSearch.eu~(OWS) in four languages (English, German, Spanish, Vietnamese), we pursue two complementary strategies. First, we apply continued pre-training to BERT models by continuing masked language modelling on unlabelled OWS texts before supervised fine-tuning, and show that this yields an average macro-F1 gain of approximately 3% over standard baselines across sixteen benchmarks, with stronger gains in low-resource settings. Second, we use four open-source LLMs (Mistral-7B, Llama3.1-8B, Gemma2-9B, Qwen2.5-14B) to produce synthetic annotations through three ensemble strategies: mean averaging, majority voting, and a LightGBM meta-learner. The LightGBM ensemble consistently outperforms the other strategies. Fine-tuning on these synthetic labels substantially benefits a small model (Llama3.2-1B: +11% pooled F1), but provides only a modest gain for the larger Qwen2.5-14B (+0.6%). Our results indicate that the combination of web-scale unlabelled data and LLM-ensemble annotations is the most valuable for smaller models and low-resource languages.

Dang H. Dang, Jelena Mitrovi, Michael Granitzer

University of Passau, Chair of Data Science

Hate Speech DetectionLow-Resource Language ProcessingSynthetic Data GenerationLanguage Model EnsemblesContinued Pretraining
AskPDF
Mar 18, 2026

Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilinguality

Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode substantial cross-lingual knowledge in a unified semantic space, they often struggle to reliably interface this knowledge with low-resource or unseen languages. Fortunately, pretrained encoder-decoder translation models already possess balanced multilingual capability, suggesting a natural complement to LLMs. In this work, we propose XBridge, a compositional encoder-LLM-decoder architecture that offloads multilingual understanding and generation to external pretrained translation models, while preserving the LLM as an English-centric core for general knowledge processing. To address the resulting representation misalignment across models, we introduce lightweight cross-model mapping layers and an optimal transport-based alignment objective, enabling fine-grained semantic consistency for multilingual generation. Experiments on four LLMs across multilingual understanding, reasoning, summarization, and generation indicate that XBridge outperforms strong baselines, especially on low-resource and previously unseen languages, without retraining the LLM.

Mengyu Bu, Yang Feng

Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS) · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences, Beijing, China

Multilingual Language ModelsCross-Lingual TransferLow-Resource Language ProcessingCross-Lingual Representation Alignment
AskPDF
Mar 17, 2026

TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human Validation

The rapid proliferation of Large Language Models (LLMs) has created a profound digital divide, effectively excluding indigenous languages of the Global South from the AI revolution. The Tharu language, an Indo-Aryan vernacular spoken by approximately 1.7 million people across the Terai belt of Nepal and India, exemplifies this crisis. Despite a rich oral tradition, Tharu suffers from severe data scarcity and linguistic fragmentation, causing state-of-the-art multilingual models to routinely "hallucinate" or default to dominant high-resource neighbors like Hindi and Nepali due to contamination in pre-training corpora. This paper presents Tharu-LLaMA (3B), a specialized instruction-following model designed to address this exclusion. We introduce TharuChat, a novel dataset constructed via a LLM-to-Human bootstrapping pipeline. We utilized prompt-engineered Gemini models, fed with Rana Tharu grammar and folklore, to synthesize training data. Unlike curated gold-standard corpora, TharuChat reflects the noisy, heterogeneous linguistic reality of the region: it is predominantly anchored in Rana Tharu (~70%) while integrating elements of Dangaura and Kochila dialects. We provide a transparent analysis of the dataset's limitations, including dialectal code-mixing and residual Awadhi/Hindi influence. Through a rigorous empirical ablation study, we demonstrate that despite these imperfections, small-scale synthetic data is highly effective, increasing the dataset volume from 25% to 100% results in a linear reduction in perplexity from 6.42 to 2.88. The resulting model serves as a proof-of-concept for the preservation of under-resourced Himalayan languages via generative AI, achievable on consumer-grade hardware.

Prajwal Panth, Agniva Maiti

School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, India

Low-Resource Language ProcessingSynthetic Data Generation for Language ModelsSmall Language Models
AskPDF
Mar 17, 2026

Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech

Cross-lingual sentence encoders typically cover only a few hundred languages and often trade downstream quality for stronger alignment, limiting their adoption. We introduce OmniSONAR, a new family of omnilingual, cross-lingual and cross-modal sentence embedding models that natively embed text, speech, code, and mathematical expressions in a single semantic space, while delivering state-of-the-art downstream performance at the scale of thousands of languages, from high-resource to extremely low-resource varieties. To reach this scale without representation collapse, we use progressive training. We first learn a strong foundational space for 200 languages with an LLM-initialized encoder-decoder, combining token-level decoding with a novel split-softmax contrastive loss and synthetic hard negatives. Building on this foundation, we expand to several thousands language varieties via a two-stage teacher-student encoder distillation framework. Finally, we demonstrate the cross-modal extensibility of this space by seamlessly mapping 177 spoken languages into it. OmniSONAR halves cross-lingual similarity search error on the 200-language FLORES dataset and reduces error by a factor of 15 on the 1,560-language BIBLE benchmark. It also enables strong translation, outperforming NLLB-3B on multilingual benchmarks and exceeding prior models (including much larger LLMs) by 15 chrF++ points on 1,560 languages into English BIBLE translation. OmniSONAR also performs strongly on MTEB and XLCoST. For speech, OmniSONAR achieves a 43% lower similarity-search error and reaches 97% of SeamlessM4T speech-to-text quality, despite being zero-shot for translation (trained only on ASR data). Finally, by training an encoder-decoder LM, Spectrum, exclusively on English text processing OmniSONAR embedding sequences, we unlock high-performance transfer to thousands of languages and speech for complex downstream tasks.

Omnilingual SONAR Team, João Maria Janeiro, Pere-Lluís Huguet Cabot +17

FAIR at Meta

Sentence EmbeddingsCross-Lingual Representation AlignmentCross-Modal Representation LearningLow-Resource Language Processing
AskPDF
Mar 17, 2026

Who Benchmarks the Benchmarks? A Case Study of LLM Evaluation in Icelandic

This paper evaluates current Large Language Model (LLM) benchmarking for Icelandic, identifies problems, and calls for improved evaluation methods in low/medium-resource languages in particular. We show that benchmarks that include synthetic or machine-translated data that have not been verified in any way, commonly contain severely flawed test examples that are likely to skew the results and undermine the tests' validity. We warn against the use of such methods without verification in low/medium-resource settings as the translation quality can, at best, only be as good as MT quality for a given language at any given time. Indeed, the results of our quantitative error analysis on existing benchmarks for Icelandic show clear differences between human-authored/-translated benchmarks vs. synthetic or machine-translated benchmarks.

Finnur Ágúst Ingimundarson, Steinunn Rut Friðriksdóttir, Bjarki Ármannsson +2

University of Zürich · University of Iceland · The Árni Magnússon Institute for Icelandic Studies

LLM EvaluationBenchmark ValidityLow-Resource Language ProcessingSynthetic Data Evaluation
AskPDF
Mar 17, 2026

PashtoCorp: A 1.25-Billion-Word Corpus, Evaluation Suite, and Reproducible Pipeline for Low-Resource Language Development

We present PashtoCorp, a 1.25-billion-word corpus for Pashto, a language spoken by 60 million people that remains severely underrepresented in NLP. The corpus is assembled from 39 sources spanning seven HuggingFace datasets and 32 purpose-built web scrapers, processed through a reproducible pipeline with Arabic-script tokenization, SHA-256 deduplication, and quality filtering. At 1.25B words across 2.81 million documents, PashtoCorp is 40x larger than the OSCAR Pashto subset and 83x larger than the previously largest dedicated Pashto corpus. Continued MLM pretraining of XLM-R-base on PashtoCorp reduces held-out perplexity by 25.1% (8.08->6.06). On WikiANN Pashto NER, the pretrained model improves entity F1 by 10% relative (19.0%->21.0%) and reduces training variance nearly 7x; the largest gain appears at 50 training sentences (+27%), with PashtoCorp covering 97.9% of WikiANN entity vocabulary. On Belebele Pashto reading comprehension, Gemma-3n achieves 64.6% accuracy, the first published LLM baseline for Pashto on this benchmark. A leave-one-out source ablation shows that Wikipedia (0.7% of documents) is the most critical source for NER: removing it alone reduces entity F1 by 47%. Corpus data, trained model, and code are available at https://huggingface.co/datasets/ihanif/pashto-corpus, https://huggingface.co/ihanif/xlmr-pashto, and https://github.com/ihanif/pashto-corpus.

Hanif Rahman

Independent Researcher

Low-Resource Language ProcessingLanguage Model Pretraining
AskPDF
Mar 17, 2026

SEAHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Southeast Asia

Hate speech detection relies heavily on linguistic resources, which are primarily available in high-resource languages such as English and Chinese, creating barriers for researchers and platforms developing tools for low-resource languages in Southeast Asia, where diverse socio-linguistic contexts complicate online hate moderation. To address this, we introduce SEAHateCheck, a pioneering dataset tailored to Indonesia, Thailand, the Philippines, and Vietnam, covering Indonesian, Tagalog, Thai, and Vietnamese. Building on HateCheck's functional testing framework and refining SGHateCheck's methods, SEAHateCheck provides culturally relevant test cases, augmented by large language models and validated by local experts for accuracy. Experiments with state-of-the-art and multilingual models revealed limitations in detecting hate speech in specific low-resource languages. In particular, Tagalog test cases showed the lowest model accuracy, likely due to linguistic complexity and limited training data. In contrast, slang-based functional tests proved the hardest, as models struggled with culturally nuanced expressions. The diagnostic insights of SEAHateCheck further exposed model weaknesses in implicit hate detection and models' struggles with counter-speech expression. As the first functional test suite for these Southeast Asian languages, this work equips researchers with a robust benchmark, advancing the development of practical, culturally attuned hate speech detection tools for inclusive online content moderation.

Ri Chi Ng, Aditi Kumaresan, Yujia Hu +1

Singapore University of Technology and Design, Singapore

Hate Speech DetectionLow-Resource Language ProcessingMultilingual Language Model Evaluation
AskPDF
Mar 16, 2026

Robust Language Identification for Romansh Varieties

The Romansh language has several regional varieties, called idioms, which sometimes have limited mutual intelligibility. Despite this linguistic diversity, there has been a lack of documented efforts to build a language identification (LID) system that can distinguish between these idioms. Since Romansh LID should also be able to recognize Rumantsch Grischun, a supra-regional variety that combines elements of several idioms, this makes for a novel and interesting classification problem. In this paper, we present a LID system for Romansh idioms based on an SVM approach. We evaluate our model on a newly curated benchmark across two domains and find that it reaches an average in-domain accuracy of 97%, enabling applications such as idiom-aware spell checking or machine translation. Our classifier is publicly available.

Charlotte Model, Sina Ahmadi, Jannis Vamvas

University of Zurich

Language IdentificationLow-Resource Language Processing
AskPDF
Mar 16, 2026

SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction

Keyphrase extraction for morphologically rich, low-resource languages remains understudied, largely due to the scarcity of suitable evaluation datasets. We address this gap for Slovak by constructing a dataset of 227,432 scientific abstracts with author-assigned keyphrases -- scraped and systematically cleaned from the Slovak Central Register of Theses -- representing a 25-fold increase over the largest prior Slovak resource and approaching the scale of established English benchmarks such as KP20K. Using this dataset, we benchmark three unsupervised baselines (YAKE, TextRank, KeyBERT with SlovakBERT embeddings) and evaluate KeyLLM, an LLM-based extraction method using GPT-3.5-turbo. Unsupervised baselines achieve at most 11.6% exact-match F1@6F1@6, with a large gap to partial matching (up to 51.5%), reflecting the difficulty of matching inflected surface forms to author-assigned keyphrases. KeyLLM narrows this exact--partial gap, producing keyphrases closer to the canonical forms assigned by authors, while manual evaluation on 100 documents (κ=0.61κ= 0.61) confirms that KeyLLM captures relevant concepts that automated exact matching underestimates. Our analysis identifies morphological mismatch as the dominant failure mode for statistical methods -- a finding relevant to other inflected languages. The dataset (https://huggingface.co/datasets/NaiveNeuron/SlovKE) and evaluation code (https://github.com/NaiveNeuron/SlovKE) are publicly available.

David Števaňák, Marek Šuppa

University of Vienna, Austria · NaiveNeuron · Faculty of Mathematics, Physics and Informatics, Comenius University in Bratislava +1

Document Information ExtractionLow-Resource Language ProcessingLLM Information Extraction
AskPDF
Mar 16, 2026

SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia

Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on high-resource languages and fail to evaluate models in realistic multilingual environments. In Southeast Asia, the diversity of languages, complex writing systems, and highly varied document types make this challenge even greater. We introduce SEA-Vision, a benchmark that jointly evaluates Document Parsing and Text-Centric Visual Question Answering (TEC-VQA) across 11 Southeast Asian languages. SEA-Vision contains 15,234 document parsing pages from nine representative document types, annotated with hierarchical page-, block-, and line-level labels. It also provides 7,496 TEC-VQA question-answer pairs that probe text recognition, numerical calculation, comparative analysis, logical reasoning, and spatial understanding. To make such multilingual, multi-task annotation feasible, we design a hybrid pipeline for Document Parsing and TEC-VQA. It combines automated filtering and scoring with MLLM-assisted labeling and lightweight native-speaker verification, greatly reducing manual labeling while maintaining high quality. We evaluate several leading multimodal models and observe pronounced performance degradation on low-resource Southeast Asian languages, highlighting substantial remaining gaps in multilingual document and scene text understanding. We believe SEA-Vision will help drive global progress in document and scene text understanding.

Pengfei Yue, Xingran Zhao, Juntao Chen +6

Xiamen University, China · Shopee, China · Tongji University, China

Multilingual VLM EvaluationDocument ParsingVisual Question AnsweringScene Text RecognitionLow-Resource Language Processing
AskPDF
Mar 16, 2026

Indirect Question Answering in English, German and Bavarian: A Challenging Task for High- and Low-Resource Languages Alike

Indirectness is a common feature of daily communication, yet is underexplored in NLP research for both low-resource as well as high-resource languages. Indirect Question Answering (IQA) aims at classifying the polarity of indirect answers. In this paper, we present two multilingual corpora for IQA of varying quality that both cover English, Standard German and Bavarian, a German dialect without standard orthography: InQA+, a small high-quality evaluation dataset with hand-annotated labels, and GenIQA, a larger training dataset, that contains artificial data generated by GPT-4o-mini. We find that IQA is a pragmatically hard task that comes with various challenges, based on several experiment variations with multilingual transformer models (mBERT, XLM-R and mDeBERTa). We suggest and employ recommendations to tackle these challenges. Our results reveal low performance, even for English, and severe overfitting. We analyse various factors that influence these results, including label ambiguity, label set and dataset size. We find that the IQA performance is poor in high- (English, German) and low-resource languages (Bavarian) and that it is beneficial to have a large amount of training data. Further, GPT-4o-mini does not possess enough pragmatic understanding to generate high-quality IQA data in any of our tested languages.

Miriam Winkler, Verena Blaschke, Barbara Plank

UMaiNLP lab, Center for Information and Language Processing, LMU Munich, Germany · ÆMunich Center for Machine Learning, Germany

Question AnsweringMultilingual QALow-Resource Language Processing
AskPDF
Mar 16, 2026

Pretraining and Benchmarking Modern Encoders for Latvian

Encoder-only transformers remain essential for practical NLP tasks. While recent advances in multilingual models have improved cross-lingual capabilities, low-resource languages such as Latvian remain underrepresented in pretraining corpora, and few monolingual Latvian encoders currently exist. We address this gap by pretraining a suite of Latvian-specific encoders based on RoBERTa, DeBERTaV3, and ModernBERT architectures, including long-context variants, and evaluating them across a diverse set of Latvian diagnostic and linguistic benchmarks. Our models are competitive with existing monolingual and multilingual encoders while benefiting from recent architectural and efficiency advances. Our best model, lv-deberta-base (111M parameters), achieves the strongest overall performance, outperforming larger multilingual baselines and prior Latvian-specific encoders. We release all pretrained models and evaluation resources to support further research and practical applications in Latvian NLP.

Arturs Znotins

Institute of Mathematics and Computer Science, University of Latvia, 29 Raina bulv., Riga, LV-1459, Latvia

Language Model PretrainingLow-Resource Language ProcessingLanguage ModelingLLM Evaluation
AskPDF
Mar 15, 2026

Parameter-Efficient Quality Estimation via Frozen Recursive Models

Tiny Recursive Models (TRM) achieve strong results on reasoning tasks through iterative refinement of a shared network. We investigate whether these recursive mechanisms transfer to Quality Estimation (QE) for low-resource languages using a three-phase methodology. Experiments on 88 language pairs on a low-resource QE dataset reveal three findings. First, TRM's recursive mechanisms do not transfer to QE. External iteration hurts performance, and internal recursion offers only narrow benefits. Next, representation quality dominates architectural choices, and lastly, frozen pretrained embeddings match fine-tuned performance while reducing trainable parameters by 37×\times (7M vs 262M). TRM-QE with frozen XLM-R embeddings achieves a Spearman's correlation of 0.370, matching fine-tuned variants (0.369) and outperforming an equivalent-depth standard transformer (0.336). On Hindi and Tamil, frozen TRM-QE outperforms MonoTransQuest (560M parameters) with 80×\times fewer trainable parameters, suggesting that weight sharing combined with frozen embeddings enables parameter efficiency for QE. We release the code publicly for further research. Code is available at https://github.com/surrey-nlp/TRMQE.

Umar Abubacar, Roman Bauer, Diptesh Kanojia

NICE Research Group, University of Surrey, UK · Surrey Institute for People-Centred AI (PAI), University of Surrey, UK

Low-Resource Language ProcessingMT EvaluationParameter-Efficient Fine-Tuning
AskPDF
Mar 15, 2026

Multilingual TinyStories: A Synthetic Combinatorial Corpus of Indic Children's Stories for Training Small Language Models

The development of robust language models for low-resource languages is frequently bottlenecked by the scarcity of high-quality, coherent, and domain-appropriate training corpora. In this paper, we introduce the Multilingual TinyStories dataset, a large-scale, synthetically generated collection of children's stories encompassing 17 Indian languages. Designed specifically for the training and evaluation of Small Language Models (SLMs), the corpus provides simple, narrative-driven text strictly localized to native scripts. We detail our hybrid curation pipeline, which leverages the Sarvam-M language model and a novel combinatorial prompt engineering framework for native generation, coupled with the Google Translate API for large-scale cross-lingual expansion. Through strict programmatic filtering, we compiled 132,942 stories and over 93.9 million tokens in our release, serving as a foundational resource for multilingual language modeling and transfer learning in the Indic linguistic sphere.

Deepon Halder, Angira Mukherjee

AI4Bharat, IIEST Shibpur · IIEST Shibpur

Synthetic Data Generation for Language ModelsLow-Resource Language ProcessingMultilingual Language ModelsSmall Language Models
AskPDF
Mar 15, 2026

CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resource programming languages primarily focuses on Domain-Specific Languages (DSLs), leaving general-purpose languages that suffer from data scarcity underexplored. To address this gap, we introduce CangjieBench, a contamination-free benchmark for Cangjie, a representative low-resource general-purpose language. The benchmark comprises 248 high-quality samples manually translated from HumanEval and ClassEval, covering both Text-to-Code and Code-to-Code tasks. We conduct a systematic evaluation of diverse LLMs under four settings: Direct Generation, Syntax-Constrained Generation, Retrieval-Augmented Generation (RAG), and Agent. Experiments reveal that Direct Generation performs poorly, whereas Syntax-Constrained Generation offers the best trade-off between accuracy and computational cost. Agent achieve state-of-the-art accuracy but incur high token consumption. Furthermore, we observe that Code-to-Code translation often underperforms Text-to-Code generation, suggesting a negative transfer phenomenon where models overfit to the source language patterns. We hope that our work will offer valuable insights into LLM generalization to unseen and low-resource programming languages. Our code and data are available at https://github.com/cjhCoder7/CangjieBench.

Junhang Cheng, Fang Liu, Jia Li +3

Beihang University, Beijing, China · Wuhan University, Wuhan, China

Code GenerationLLM Code GenerationLow-Resource Language ProcessingLLM EvaluationCode Translation
AskPDF
Mar 15, 2026

Vavanagi: a Community-run Platform for Documentation of the Hula Language in Papua New Guinea

We present Vavanagi, a community-run platform for Hula (Vula'a), an Austronesian language of Papua New Guinea with approximately 10,000 speakers. Vavanagi supports crowdsourced English-Hula text translation and voice recording, with elder-led review and community-governed data infrastructure. To date, 77 translators and 4 reviewers have produced over 12k parallel sentence pairs covering 9k unique Hula words. We also propose a multi-level framework for measuring community involvement, from consultation to fully community-initiated and governed projects. We position Vavanagi at Level 5: initiative, design, implementation, and data governance all sit within the Hula community, making it, to our knowledge, the first community-led language technology initiative for a language of this size. Vavanagi shows how language technology can bridge village-based and urban members, connect generations, and support cultural heritage on the community's own terms.

Bri Olewale, Raphael Merx, Ekaterina Vylomova

Vula’a Kunenai Community, Central Province, Papua New Guinea · The University of Melbourne, Melbourne, Australia

Low-Resource Language Processing
AskPDF
Mar 14, 2026

OasisSimp: An Open-source Asian-English Sentence Simplification Dataset

Sentence simplification aims to make complex text more accessible by reducing linguistic complexity while preserving the original meaning. However, progress in this area remains limited for mid-resource and low-resource languages due to the scarcity of high-quality data. To address this gap, we introduce the OasisSimp dataset, a multilingual dataset for sentence-level simplification covering five languages: English, Sinhala, Tamil, Pashto, and Thai. Among these, no prior sentence simplification datasets exist for Thai, Pashto, and Tamil, while limited data is available for Sinhala. Each language simplification dataset was created by trained annotators who followed detailed guidelines to simplify sentences while maintaining meaning, fluency, and grammatical correctness. We evaluate eight open-weight multilingual Large Language Models (LLMs) on the OasisSimp dataset and observe substantial performance disparities between high-resource and low-resource languages, highlighting the simplification challenges in multilingual settings. The OasisSimp dataset thus provides both a valuable multilingual resource and a challenging benchmark, revealing the limitations of current LLM-based simplification methods and paving the way for future research in low-resource sentence simplification. The dataset is available at https://OasisSimpDataset.github.io/.

Hannah Liu, Muxin Tian, Iqra Ali +8

University of Toronto · Queen Mary University of London · Yale University +5

Text SimplificationLow-Resource Language ProcessingMultilingual Language ModelsMultilingual Language Model Evaluation
AskPDF
Mar 14, 2026

GhanaNLP Parallel Corpora: Comprehensive Multilingual Resources for Low-Resource Ghanaian Languages

Low resource languages present unique challenges for natural language processing due to the limited availability of digitized and well structured linguistic data. To address this gap, the GhanaNLP initiative has developed and curated 41,513 parallel sentence pairs for the Twi, Fante, Ewe, Ga, and Kusaal languages, which are widely spoken across Ghana yet remain underrepresented in digital spaces. Each dataset consists of carefully aligned sentence pairs between a local language and English. The data were collected, translated, and annotated by human professionals and enriched with standard structural metadata to ensure consistency and usability. These corpora are designed to support research, educational, and commercial applications, including machine translation, speech technologies, and language preservation. This paper documents the dataset creation methodology, structure, intended use cases, and evaluation, as well as their deployment in real world applications such as the Khaya AI translation engine. Overall, this work contributes to broader efforts to democratize AI by enabling inclusive and accessible language technologies for African languages.

Lawrence Adu Gyamfi, Paul Azunre, Stephen Edward Moore +4

Ghana Natural Language Processing, Ghana · Khaya AI LTD, Ghana · Department of Mathematics, University of Cape Coast, Cape Coast, Ghana

African Language ProcessingLow-Resource Language ProcessingLow-Resource MT
AskPDF
Mar 13, 2026

Cross-Lingual Transfer and Parameter-Efficient Adaptation in the Turkic Language Family: A Theoretical Framework for Low-Resource Language Models

Large language models (LLMs) have transformed natural language processing, yet their capabilities remain uneven across languages. Most multilingual models are trained primarily on high-resource languages, leaving many languages with large speaker populations underrepresented in both training data and evaluation benchmarks. This imbalance is particularly visible in the Turkic language family. This paper proposes a theoretical framework for studying cross-lingual transfer and parameter-efficient adaptation of multilingual LLMs within the Turkic language family, focusing on Azerbaijani, Kazakh, Uzbek, Turkmen, and Gagauz. These languages share substantial typological and morphological similarity while differing greatly in available digital resources, making them a natural setting for analyzing multilingual adaptation strategies. We integrate insights from multilingual representation learning and parameter-efficient fine-tuning techniques such as Low-Rank Adaptation (LoRA) to develop a conceptual scaling model describing how adaptation performance depends on model capacity, adaptation data size, and the expressivity of adaptation modules. To formalize transfer potential between related languages, we introduce the Turkic Transfer Coefficient (TTC), a theoretical measure incorporating morphological similarity, lexical overlap, syntactic structure, and script compatibility across Turkic languages. The framework highlights how typological similarity can enable efficient multilingual transfer while also identifying structural limits of parameter-efficient adaptation in extremely low-resource scenarios.

O. Ibrahimzade, K. Tabasaransky

Cross-Lingual TransferMultilingual Language ModelsLow-Resource Language ProcessingParameter-Efficient Fine-Tuning
AskPDF
Mar 11, 2026

MUNIChus: Multilingual News Image Captioning Benchmark

The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and visual elements. The majority of research on news image captioning focuses on English, primarily because datasets in other languages are scarce. To address this limitation, we create the first multilingual news image captioning benchmark, MUNIChus, comprising 9 languages, including several low-resource languages such as Sinhala and Urdu. We evaluate various state-of-the-art neural news image captioning models on MUNIChus and find that news image captioning remains challenging. We also make MUNIChus publicly available with over 20 models already benchmarked. MUNIChus opens new avenues for further advancements in developing and evaluating multilingual news image captioning models.

Yuji Chen, Alistair Plum, Hansi Hettiarachchi +4

Lancaster University, UK · University of Luxembourg, Luxembourg · University of Surrey, UK +1

Image CaptioningMultilingual VLM EvaluationLow-Resource Language Processing
AskPDF