Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Parameter-Efficient Fine-Tuning for LLM-Based Arabic-to-English Machine Translation

Domain:

natural language processing

Record type:

paper
Creator:
AmiBahAli
Publisher:
Fac
Host:avatar
Large Language Models (LLMs) such as GPT-3, BLOOM, BERT... have revolutionized natural language processing (NLP), particularly in translation. However, fine-tuning these models for downstream tasks, such as Arabic-to-English translation, requires extensive computational resources. Traditional full fine-tuning methods that involve updating all parameters of the model pose significant computational and memory challenges, notably for models with billions of parameters. This study investigates the application of LoRA-based PEFT methods on two chosen models for Arabic to English translation, AraT5 and NLLB-200, with a focus on understanding the trade-offs between computational efficiency and translation quality.

Visit

doi.orgzenodo.org

Tasks

machine translation

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similar

IncreLoRA: Incremental Parameter Allocation Method for Parameter-Efficient Fine-tuningC-EB/Fine-Tuning-mBART-for-Darija-to-English-TranslationParameter-Efficient Fine-Tuning for Equitable Named Entity Recognition in African Languages: A Lora-Based ApproachGradient-Based Importance Smoothing for Dynamic Rank Allocation in Parameter-Efficient Fine-Tuning for Low-Resource Languages<p>Low-Resource Machine Translation of Yoruba Text to Nigerian Pidgin Using NLLB-200 and Parameter-Efficient Fine-Tuning</p>Parameter-Efficient Tuning vs. Full Fine-Tuning in Cross-Lingual Dense Retrieval for Low-Resource Languages

IncreLoRA: Incremental Parameter Allocation Method for Parameter-Efficient Fine-tuning

With the increasing size of pre-trained language models (PLMs), fine-tuning all the parameters in th

C-EB/Fine-Tuning-mBART-for-Darija-to-English-Translation

Fine-tuning mBART for Moroccan Darija–English translation using a custom parallel dataset, with a de

Parameter-Efficient Fine-Tuning for Equitable Named Entity Recognition in African Languages: A Lora-Based Approach

Named entity recognition (NER) remains a challenge for Africa

Gradient-Based Importance Smoothing for Dynamic Rank Allocation in Parameter-Efficient Fine-Tuning for Low-Resource Languages

Abstract Large pre-trained language models (PLMs) achieve state-of-the-art perform

<p>Low-Resource Machine Translation of Yoruba Text to Nigerian Pidgin Using NLLB-200 and Parameter-Efficient Fine-Tuning</p>

Parameter-Efficient Tuning vs. Full Fine-Tuning in Cross-Lingual Dense Retrieval for Low-Resource Languages

Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language model