University of Pretoria
Browse

Prompt engineering on large language models (LLMs) in low-resourced language setting

Version 2 2025-10-13, 14:11
Version 1 2025-10-13, 14:03
dataset
posted on 2025-10-13, 14:11 authored by Pitso KhobokoPitso Khoboko
<p dir="ltr">The attached dataset has all the information in regard to Large Language Models (LLMs) being used in low-resource language settings. There are figures depicting the prompt structure used to improve translation of LLMs translation of low-resourced languages, more specifically, low-resourced, morphologically rich African languages. Furthermore, there are figures that depict the results of various experiments conducted in efforts to improve LLMs' translation of low-resourced languages, and there are clean evaluation datasets that can be used by other researchers to evaluate their LLMs in low-resourced language settings.</p>

Funding

General Studentship Masters Bursary, University of Pretoria (UP)

General Post-Assistance Data Science for Social Impact, University of Pretoria (UP)

History

Related Materials

  1. 1.

Department/Unit/School/Center

Computer Science

Sustainable Development Goals

  • 4 Quality Education
  • 10 Reduced Inequalities