@inproceedings{pourmostafa-roshan-sharami-etal-2024-guiding,
title = "Guiding In-Context Learning of {LLM}s through Quality Estimation for Machine Translation",
author = "Pourmostafa Roshan Sharami, Javad and
Shterionov, Dimitar and
Spronck, Pieter",
editor = "Knowles, Rebecca and
Eriguchi, Akiko and
Goel, Shivali",
booktitle = "Proceedings of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)",
month = sep,
year = "2024",
address = "Chicago, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2024.amta-research.9",
pages = "88--101",
abstract = "The quality of output from large language models (LLMs), particularly in machine translation (MT), is closely tied to the quality of in-context examples (ICEs) provided along with the query, i.e., the text to translate. The effectiveness of these ICEs is influenced by various factors, such as the domain of the source text, the order in which the ICEs are presented, the number of these examples, and the prompt templates used. Naturally, selecting the most impactful ICEs depends on understanding how these affect the resulting translation quality, which ultimately relies on translation references or human judgment. This paper presents a novel methodology for in-context learning (ICL) that relies on a search algorithm guided by domain-specific quality estimation (QE). Leveraging the XGLM model, our methodology estimates the resulting translation quality without the need for translation references, selecting effective ICEs for MT to maximize translation quality. Our results demonstrate significant improvements over existing ICL methods and higher translation performance compared to fine-tuning a pre-trained language model (PLM), specifically mBART-50.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pourmostafa-roshan-sharami-etal-2024-guiding">
<titleInfo>
<title>Guiding In-Context Learning of LLMs through Quality Estimation for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Javad</namePart>
<namePart type="family">Pourmostafa Roshan Sharami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Shterionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pieter</namePart>
<namePart type="family">Spronck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Knowles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Eriguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivali</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Chicago, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The quality of output from large language models (LLMs), particularly in machine translation (MT), is closely tied to the quality of in-context examples (ICEs) provided along with the query, i.e., the text to translate. The effectiveness of these ICEs is influenced by various factors, such as the domain of the source text, the order in which the ICEs are presented, the number of these examples, and the prompt templates used. Naturally, selecting the most impactful ICEs depends on understanding how these affect the resulting translation quality, which ultimately relies on translation references or human judgment. This paper presents a novel methodology for in-context learning (ICL) that relies on a search algorithm guided by domain-specific quality estimation (QE). Leveraging the XGLM model, our methodology estimates the resulting translation quality without the need for translation references, selecting effective ICEs for MT to maximize translation quality. Our results demonstrate significant improvements over existing ICL methods and higher translation performance compared to fine-tuning a pre-trained language model (PLM), specifically mBART-50.</abstract>
<identifier type="citekey">pourmostafa-roshan-sharami-etal-2024-guiding</identifier>
<location>
<url>https://aclanthology.org/2024.amta-research.9</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>88</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Guiding In-Context Learning of LLMs through Quality Estimation for Machine Translation
%A Pourmostafa Roshan Sharami, Javad
%A Shterionov, Dimitar
%A Spronck, Pieter
%Y Knowles, Rebecca
%Y Eriguchi, Akiko
%Y Goel, Shivali
%S Proceedings of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)
%D 2024
%8 September
%I Association for Machine Translation in the Americas
%C Chicago, USA
%F pourmostafa-roshan-sharami-etal-2024-guiding
%X The quality of output from large language models (LLMs), particularly in machine translation (MT), is closely tied to the quality of in-context examples (ICEs) provided along with the query, i.e., the text to translate. The effectiveness of these ICEs is influenced by various factors, such as the domain of the source text, the order in which the ICEs are presented, the number of these examples, and the prompt templates used. Naturally, selecting the most impactful ICEs depends on understanding how these affect the resulting translation quality, which ultimately relies on translation references or human judgment. This paper presents a novel methodology for in-context learning (ICL) that relies on a search algorithm guided by domain-specific quality estimation (QE). Leveraging the XGLM model, our methodology estimates the resulting translation quality without the need for translation references, selecting effective ICEs for MT to maximize translation quality. Our results demonstrate significant improvements over existing ICL methods and higher translation performance compared to fine-tuning a pre-trained language model (PLM), specifically mBART-50.
%U https://aclanthology.org/2024.amta-research.9
%P 88-101
Markdown (Informal)
[Guiding In-Context Learning of LLMs through Quality Estimation for Machine Translation](https://aclanthology.org/2024.amta-research.9) (Pourmostafa Roshan Sharami et al., AMTA 2024)
ACL