# In-Domain African Languages Translation Using LLMs and Multi-armed Bandits

arXiv: https://arxiv.org/abs/2505.15069 · HTML: https://mlsanity.com/paper/2505.15069/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 29 of 29)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [Simple, Scalable Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1909.08478/) (2019)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs](https://mlsanity.com/paper/1911.06154/) (2019)
- [SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization](https://mlsanity.com/paper/2106.01890/) (2021)
- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation](https://mlsanity.com/paper/2205.02022/) (2022)
- [The unreasonable effectiveness of few-shot learning for machine translation](https://mlsanity.com/paper/2302.01398/) (2023)
- [Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback](https://mlsanity.com/paper/1707.07402/) (2017)
- [Neural Contextual Bandits with Deep Representation and Shallow Exploration](https://mlsanity.com/paper/2012.01780/) (2020)
- [A Survey of Domain Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1806.00258/) (2018)
- [SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization](https://mlsanity.com/paper/2203.06569/) (2022)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Domain Control for Neural Machine Translation](https://mlsanity.com/paper/1612.06140/) (2016)
- [Improving Robustness of Machine Translation with Synthetic Noise](https://mlsanity.com/paper/1902.09508/) (2019)
- [A Survey on Contextual Multi-armed Bandits](https://mlsanity.com/paper/1508.03326/) (2015)
- [Domain Adaptation of Neural Machine Translation by Lexicon Induction](https://mlsanity.com/paper/1906.00376/) (2019)
- [Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2105.03953/) (2021)
- [A survey on multi-player bandits](https://mlsanity.com/paper/2211.16275/) (2022)
- [Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation](https://mlsanity.com/paper/2004.02577/) (2020)
- [Adaptation of Machine Translation Models with Back-translated Data using Transductive Data Selection Methods](https://mlsanity.com/paper/1906.07808/) (2019)
- [Incorporating Bilingual Dictionaries for Low Resource Semi-Supervised Neural Machine Translation](https://mlsanity.com/paper/2004.02071/) (2020)
- [Multi-Domain Adaptation in Neural Machine Translation Through Multidimensional Tagging](https://mlsanity.com/paper/2102.10160/) (2021)
- [Faster Machine Translation Ensembling with Reinforcement Learning and Competitive Correction](https://mlsanity.com/paper/2501.15219/) (2025)

## Abstract (arXiv)

Neural Machine Translation (NMT) systems face significant challenges when working with low-resource languages, particularly in domain adaptation tasks. These difficulties arise due to limited training data and suboptimal model generalization, As a result, selecting an optimal model for translation is crucial for achieving strong performance on in-domain data, particularly in scenarios where fine-tuning is not feasible or practical. In this paper, we investigate strategies for selecting the most suitable NMT model for a given domain using bandit-based algorithms, including Upper Confidence Bound, Linear UCB, Neural Linear Bandit, and Thompson Sampling. Our method effectively addresses the resource constraints by facilitating optimal model selection with high confidence. We evaluate the approach across three African languages and domains, demonstrating its robustness and effectiveness in both scenarios where target data is available and where it is absent.