@inproceedings{zeng-etal-2024-towards,
title = "Towards Multiple References Era {--} Addressing Data Leakage and Limited Reference Diversity in Machine Translation Evaluation",
author = "Zeng, Xianfeng and
Liu, Yijin and
Meng, Fandong and
Zhou, Jie",
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.710",
pages = "11939--11951",
abstract = "Recent research has shown a weak correlation between n-gram-based metrics and human evaluations in machine translation task, particularly when evaluating large language models (LLMs). Additionally, the data leakage risk in LLMs may cause an overestimation problem when evaluating LLMs on downstream tasks. In this work, we identify the limited diversity of references as the primary cause for the inferior performance of n-gram-based metrics and the overestimation problem. To address this issue, we propose to utilize multiple references generated by LLMs, coupled with an effective selection strategy focused on accuracy and diversity, to improve the alignment between automatic metrics and human evaluations. We validate our approach on the WMT22 Metrics benchmark with 4 languages and observe a maximum accuracy gain of 9.5{\%} in F200spBLEU, which makes it on par with computationally expensive neural-based metrics. We also show that using multi-reference with n-gram-based metrics significantly alleviates the overestimation problem when evaluating LLMs with data leakage. Further analysis explores the factors that affect the quality of generated references, offering insights into data synthesis by LLMs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2024-towards">
<titleInfo>
<title>Towards Multiple References Era – Addressing Data Leakage and Limited Reference Diversity in Machine Translation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xianfeng</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fandong</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</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 research has shown a weak correlation between n-gram-based metrics and human evaluations in machine translation task, particularly when evaluating large language models (LLMs). Additionally, the data leakage risk in LLMs may cause an overestimation problem when evaluating LLMs on downstream tasks. In this work, we identify the limited diversity of references as the primary cause for the inferior performance of n-gram-based metrics and the overestimation problem. To address this issue, we propose to utilize multiple references generated by LLMs, coupled with an effective selection strategy focused on accuracy and diversity, to improve the alignment between automatic metrics and human evaluations. We validate our approach on the WMT22 Metrics benchmark with 4 languages and observe a maximum accuracy gain of 9.5% in F200spBLEU, which makes it on par with computationally expensive neural-based metrics. We also show that using multi-reference with n-gram-based metrics significantly alleviates the overestimation problem when evaluating LLMs with data leakage. Further analysis explores the factors that affect the quality of generated references, offering insights into data synthesis by LLMs.</abstract>
<identifier type="citekey">zeng-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.710</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11939</start>
<end>11951</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Multiple References Era – Addressing Data Leakage and Limited Reference Diversity in Machine Translation Evaluation
%A Zeng, Xianfeng
%A Liu, Yijin
%A Meng, Fandong
%A Zhou, Jie
%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 zeng-etal-2024-towards
%X Recent research has shown a weak correlation between n-gram-based metrics and human evaluations in machine translation task, particularly when evaluating large language models (LLMs). Additionally, the data leakage risk in LLMs may cause an overestimation problem when evaluating LLMs on downstream tasks. In this work, we identify the limited diversity of references as the primary cause for the inferior performance of n-gram-based metrics and the overestimation problem. To address this issue, we propose to utilize multiple references generated by LLMs, coupled with an effective selection strategy focused on accuracy and diversity, to improve the alignment between automatic metrics and human evaluations. We validate our approach on the WMT22 Metrics benchmark with 4 languages and observe a maximum accuracy gain of 9.5% in F200spBLEU, which makes it on par with computationally expensive neural-based metrics. We also show that using multi-reference with n-gram-based metrics significantly alleviates the overestimation problem when evaluating LLMs with data leakage. Further analysis explores the factors that affect the quality of generated references, offering insights into data synthesis by LLMs.
%U https://aclanthology.org/2024.findings-acl.710
%P 11939-11951
Markdown (Informal)
[Towards Multiple References Era – Addressing Data Leakage and Limited Reference Diversity in Machine Translation Evaluation](https://aclanthology.org/2024.findings-acl.710) (Zeng et al., Findings 2024)
ACL