@inproceedings{chitale-etal-2024-empirical,
title = "An Empirical Study of In-context Learning in {LLM}s for Machine Translation",
author = "Chitale, Pranjal and
Gala, Jay and
Dabre, Raj",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.440",
pages = "7384--7406",
abstract = "Recent interest has surged in employing Large Language Models (LLMs) for machine translation (MT) via in-context learning (ICL) (Vilar et al., 2023). Most prior studies primarily focus on optimizing translation quality, with limited attention to understanding the specific aspects of ICL that influence the said quality. To this end, we perform the first of its kind, exhaustive study of in-context learning for machine translation (MT). We first establish that ICL is primarily example-driven and not instruction-driven. Following this, we conduct an extensive exploration of various aspects of the examples to understand their influence on downstream performance. Our analysis includes factors such as quality and quantity of demonstrations, spatial proximity, and source versus target originality. Further, we also investigate challenging scenarios involving indirectness and misalignment of examples to understand the limits of ICL. While we establish the significance of the quality of the target distribution over the source distribution of demonstrations, we further observe that perturbations sometimes act as regularizers, resulting in performance improvements. Surprisingly, ICL does not necessitate examples from the same task, and a related task with the same target distribution proves sufficient. We hope that our study acts as a guiding resource for considerations in utilizing ICL for MT. Our code is available on https://github.com/PranjalChitale/in-context-mt-analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chitale-etal-2024-empirical">
<titleInfo>
<title>An Empirical Study of In-context Learning in LLMs for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pranjal</namePart>
<namePart type="family">Chitale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Gala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent interest has surged in employing Large Language Models (LLMs) for machine translation (MT) via in-context learning (ICL) (Vilar et al., 2023). Most prior studies primarily focus on optimizing translation quality, with limited attention to understanding the specific aspects of ICL that influence the said quality. To this end, we perform the first of its kind, exhaustive study of in-context learning for machine translation (MT). We first establish that ICL is primarily example-driven and not instruction-driven. Following this, we conduct an extensive exploration of various aspects of the examples to understand their influence on downstream performance. Our analysis includes factors such as quality and quantity of demonstrations, spatial proximity, and source versus target originality. Further, we also investigate challenging scenarios involving indirectness and misalignment of examples to understand the limits of ICL. While we establish the significance of the quality of the target distribution over the source distribution of demonstrations, we further observe that perturbations sometimes act as regularizers, resulting in performance improvements. Surprisingly, ICL does not necessitate examples from the same task, and a related task with the same target distribution proves sufficient. We hope that our study acts as a guiding resource for considerations in utilizing ICL for MT. Our code is available on https://github.com/PranjalChitale/in-context-mt-analysis.</abstract>
<identifier type="citekey">chitale-etal-2024-empirical</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.440</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>7384</start>
<end>7406</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Empirical Study of In-context Learning in LLMs for Machine Translation
%A Chitale, Pranjal
%A Gala, Jay
%A Dabre, Raj
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F chitale-etal-2024-empirical
%X Recent interest has surged in employing Large Language Models (LLMs) for machine translation (MT) via in-context learning (ICL) (Vilar et al., 2023). Most prior studies primarily focus on optimizing translation quality, with limited attention to understanding the specific aspects of ICL that influence the said quality. To this end, we perform the first of its kind, exhaustive study of in-context learning for machine translation (MT). We first establish that ICL is primarily example-driven and not instruction-driven. Following this, we conduct an extensive exploration of various aspects of the examples to understand their influence on downstream performance. Our analysis includes factors such as quality and quantity of demonstrations, spatial proximity, and source versus target originality. Further, we also investigate challenging scenarios involving indirectness and misalignment of examples to understand the limits of ICL. While we establish the significance of the quality of the target distribution over the source distribution of demonstrations, we further observe that perturbations sometimes act as regularizers, resulting in performance improvements. Surprisingly, ICL does not necessitate examples from the same task, and a related task with the same target distribution proves sufficient. We hope that our study acts as a guiding resource for considerations in utilizing ICL for MT. Our code is available on https://github.com/PranjalChitale/in-context-mt-analysis.
%U https://aclanthology.org/2024.findings-acl.440
%P 7384-7406
Markdown (Informal)
[An Empirical Study of In-context Learning in LLMs for Machine Translation](https://aclanthology.org/2024.findings-acl.440) (Chitale et al., Findings 2024)
ACL