UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fiaz, Layba, Tahir, Munief Hassan, Shams, Sana, Hussain, Sarmad
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912243916996608
author Fiaz, Layba
Tahir, Munief Hassan
Shams, Sana
Hussain, Sarmad
author_facet Fiaz, Layba
Tahir, Munief Hassan
Shams, Sana
Hussain, Sarmad
contents Multilingual Large Language Models (LLMs) often provide suboptimal performance on low-resource languages like Urdu. This paper introduces UrduLLaMA 1.0, a model derived from the open-source Llama-3.1-8B-Instruct architecture and continually pre-trained on 128 million Urdu tokens, capturing the rich diversity of the language. To enhance instruction-following and translation capabilities, we leverage Low-Rank Adaptation (LoRA) to fine tune the model on 41,000 Urdu instructions and approximately 50,000 English-Urdu translation pairs. Evaluation across three machine translation datasets demonstrates significant performance improvements compared to state-of-the-art (SOTA) models, establishing a new benchmark for Urdu LLMs. These findings underscore the potential of targeted adaptation strategies with limited data and computational resources to address the unique challenges of low-resource languages.
format Preprint
id arxiv_https___arxiv_org_abs_2502_16961
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings
Fiaz, Layba
Tahir, Munief Hassan
Shams, Sana
Hussain, Sarmad
Computation and Language
Artificial Intelligence
I.2.7
Multilingual Large Language Models (LLMs) often provide suboptimal performance on low-resource languages like Urdu. This paper introduces UrduLLaMA 1.0, a model derived from the open-source Llama-3.1-8B-Instruct architecture and continually pre-trained on 128 million Urdu tokens, capturing the rich diversity of the language. To enhance instruction-following and translation capabilities, we leverage Low-Rank Adaptation (LoRA) to fine tune the model on 41,000 Urdu instructions and approximately 50,000 English-Urdu translation pairs. Evaluation across three machine translation datasets demonstrates significant performance improvements compared to state-of-the-art (SOTA) models, establishing a new benchmark for Urdu LLMs. These findings underscore the potential of targeted adaptation strategies with limited data and computational resources to address the unique challenges of low-resource languages.
title UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings
topic Computation and Language
Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2502.16961