On Instruction-Finetuning Neural Machine Translation Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Raunak, Vikas, Grundkiewicz, Roman, Junczys-Dowmunt, Marcin
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913535971295232
author Raunak, Vikas
Grundkiewicz, Roman
Junczys-Dowmunt, Marcin
author_facet Raunak, Vikas
Grundkiewicz, Roman
Junczys-Dowmunt, Marcin
contents In this work, we introduce instruction finetuning for Neural Machine Translation (NMT) models, which distills instruction following capabilities from Large Language Models (LLMs) into orders-of-magnitude smaller NMT models. Our instruction-finetuning recipe for NMT models enables customization of translations for a limited but disparate set of translation-specific tasks. We show that NMT models are capable of following multiple instructions simultaneously and demonstrate capabilities of zero-shot composition of instructions. We also show that through instruction finetuning, traditionally disparate tasks such as formality-controlled machine translation, multi-domain adaptation as well as multi-modal translations can be tackled jointly by a single instruction finetuned NMT model, at a performance level comparable to LLMs such as GPT-3.5-Turbo. To the best of our knowledge, our work is among the first to demonstrate the instruction-following capabilities of traditional NMT models, which allows for faster, cheaper and more efficient serving of customized translations.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05553
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On Instruction-Finetuning Neural Machine Translation Models
Raunak, Vikas
Grundkiewicz, Roman
Junczys-Dowmunt, Marcin
Computation and Language
Artificial Intelligence
In this work, we introduce instruction finetuning for Neural Machine Translation (NMT) models, which distills instruction following capabilities from Large Language Models (LLMs) into orders-of-magnitude smaller NMT models. Our instruction-finetuning recipe for NMT models enables customization of translations for a limited but disparate set of translation-specific tasks. We show that NMT models are capable of following multiple instructions simultaneously and demonstrate capabilities of zero-shot composition of instructions. We also show that through instruction finetuning, traditionally disparate tasks such as formality-controlled machine translation, multi-domain adaptation as well as multi-modal translations can be tackled jointly by a single instruction finetuned NMT model, at a performance level comparable to LLMs such as GPT-3.5-Turbo. To the best of our knowledge, our work is among the first to demonstrate the instruction-following capabilities of traditional NMT models, which allows for faster, cheaper and more efficient serving of customized translations.
title On Instruction-Finetuning Neural Machine Translation Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.05553