@inproceedings{tiwari-etal-2026-sample,
    title = "Sample-Size Scaling of the {A}frican Languages {NLI} Evaluation",
    author = "Tiwari, Anuj  and
      Ogunremu, Oluwapelumi  and
      Oko-odion, Terry  and
      Egbewale, Jesujuwon  and
      Nwokocha, Hannah Sopuruchi",
    editor = "Chimoto, Everlyn Asiko  and
      Lignos, Constantine  and
      Muhammad, Shamsuddeen  and
      Abdulmumin, Idris  and
      Siro, Clemencia  and
      Adelani, David Ifeoluwa",
    booktitle = "Proceedings of the 7th Workshop on {A}frican Natural Language Processing ({A}frica{NLP} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.africanlp-main.22/",
    pages = "217--227",
    ISBN = "979-8-89176-364-7",
    abstract = "African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance. The study is a systematic sample-size scaling study of natural language inference (NLI) on 16 African languages based on the AfriXNLI benchmark. Under controlled conditions, two multilingual transformer models with roughly 0.6B parameters XLM-R Large fine-tuned on XNLI and AfroXLM-R Large are tested on sample sizes of between 50 and 500 labeled examples and average their results across random subsampling runs. As opposed to the usual belief of monotonic increase with increased data, we find a strongly language-sensitive and often non-monotonic scaling behavior. Some languages show early saturation or decrease in performance with sample size as well as high variance in low resource regimes. These results indicate that the volume of data is not enough to guarantee stable profits to African NLI, creating the necessity of language-sensitive datasets creation and stronger multi-lingual modelling strategies."
}