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

• URL: http://arxiv.org/abs/2603.20732v1
• Date: Sat, 21 Mar 2026 09:35:40 GMT
• Title: MzansiText and MzansiLM: An Open Corpus and Decoder-Only Language Model for South African Languages
• Abstract summary: We focus on the languages of South Africa, where we are not aware of a publicly available decoder-only model that targets all eleven official written languages.<n>We introduce MzansiText, a curated multilingual pretraining corpus with a reproducible filtering pipeline, and MzansiLM, a 125M- parameter language model trained from scratch.<n>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.
• Score: 7.256099340300146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models [89.13128402847943]
  We present LUSIFER, a novel zero-shot approach that adapts LLM-based embedding models for multilingual tasks without requiring multilingual supervision.<n>LUSIFER's architecture combines a multilingual encoder, serving as a language-universal learner, with an LLM-based embedding model optimized for embedding-specific tasks.<n>We introduce a new benchmark encompassing 5 primary embedding tasks, 123 diverse datasets, and coverage across 14 languages.
  arXiv  Detail & Related papers  (2025-01-01T15:43:07Z)
• Accelerating Multilingual Language Model for Excessively Tokenized Languages [3.5570874721859016]
  tokenizers in large language models (LLMs) often fragment a text into character or Unicode-level tokens in non-Roman alphabetic languages. We introduce a simple yet effective framework to accelerate text generation in such languages.
  arXiv  Detail & Related papers  (2024-01-19T12:26:57Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• MasakhaNEWS: News Topic Classification for African languages [15.487928928173098]
  African languages are severely under-represented in NLP research due to lack of datasets covering several NLP tasks. We develop MasakhaNEWS -- a new benchmark dataset for news topic classification covering 16 languages widely spoken in Africa.
  arXiv  Detail & Related papers  (2023-04-19T21:12:23Z)
• Crosslingual Generalization through Multitask Finetuning [80.8822603322471]
  Multitask prompted finetuning (MTF) has been shown to help large language models generalize to new tasks in a zero-shot setting. We apply MTF to the pretrained multilingual BLOOM and mT5 model families to produce finetuned variants called BLOOMZ and mT0. We find finetuning large multilingual language models on English tasks with English prompts allows for task generalization to non-English languages.
  arXiv  Detail & Related papers  (2022-11-03T13:19:32Z)
• Generalizing Multimodal Pre-training into Multilingual via Language Acquisition [54.69707237195554]
  English-based Vision-Language Pre-training has achieved great success in various downstream tasks. Some efforts have been taken to generalize this success to non-English languages through Multilingual Vision-Language Pre-training. We propose a textbfMultitextbfLingual textbfAcquisition (MLA) framework that can easily generalize a monolingual Vision-Language Pre-training model into multilingual.
  arXiv  Detail & Related papers  (2022-05-29T08:53:22Z)
• 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)
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
  Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages. We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
  arXiv  Detail & Related papers  (2020-12-31T11:37:28Z)
• Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation [105.41167108465085]
  Cross-lingual Machine Reading (CLMRC) remains a challenging problem due to the lack of large-scale datasets in low-source languages. We propose a novel augmentation approach named Language Branch Machine Reading (LBMRC) LBMRC trains multiple machine reading comprehension (MRC) models proficient in individual language. We devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages.
  arXiv  Detail & Related papers  (2020-10-27T13:12:17Z)

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.