@inproceedings{kocmi-federmann-2023-large,
title = "Large Language Models Are State-of-the-Art Evaluators of Translation Quality",
author = "Kocmi, Tom and
Federmann, Christian",
editor = "Nurminen, Mary and
Brenner, Judith and
Koponen, Maarit and
Latomaa, Sirkku and
Mikhailov, Mikhail and
Schierl, Frederike and
Ranasinghe, Tharindu and
Vanmassenhove, Eva and
Vidal, Sergi Alvarez and
Aranberri, Nora and
Nunziatini, Mara and
Escart{\'\i}n, Carla Parra and
Forcada, Mikel and
Popovic, Maja and
Scarton, Carolina and
Moniz, Helena",
booktitle = "Proceedings of the 24th Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2023",
address = "Tampere, Finland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2023.eamt-1.19",
pages = "193--203",
abstract = "We describe GEMBA, a GPT-based metric for assessment of translation quality, which works both with a reference translation and without. In our evaluation, we focus on zero-shot prompting, comparing four prompt variants in two modes, based on the availability of the reference. We investigate seven versions of GPT models, including ChatGPT. We show that our method for translation quality assessment only works with GPT 3.5 and larger models. Comparing to results from WMT22{'}s Metrics shared task, our method achieves state-of-the-art accuracy in both modes when compared to MQM-based human labels. Our results are valid on the system level for all three WMT22 Metrics shared task language pairs, namely English into German, English into Russian, and Chinese into English. This provides a first glimpse into the usefulness of pre-trained, generative large language models for quality assessment of translations. We publicly release all our code and prompt templates used for the experiments described in this work, as well as all corresponding scoring results, to allow for external validation and reproducibility.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kocmi-federmann-2023-large">
<titleInfo>
<title>Large Language Models Are State-of-the-Art Evaluators of Translation Quality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Brenner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirkku</namePart>
<namePart type="family">Latomaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederike</namePart>
<namePart type="family">Schierl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="given">Alvarez</namePart>
<namePart type="family">Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Nunziatini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tampere, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe GEMBA, a GPT-based metric for assessment of translation quality, which works both with a reference translation and without. In our evaluation, we focus on zero-shot prompting, comparing four prompt variants in two modes, based on the availability of the reference. We investigate seven versions of GPT models, including ChatGPT. We show that our method for translation quality assessment only works with GPT 3.5 and larger models. Comparing to results from WMT22’s Metrics shared task, our method achieves state-of-the-art accuracy in both modes when compared to MQM-based human labels. Our results are valid on the system level for all three WMT22 Metrics shared task language pairs, namely English into German, English into Russian, and Chinese into English. This provides a first glimpse into the usefulness of pre-trained, generative large language models for quality assessment of translations. We publicly release all our code and prompt templates used for the experiments described in this work, as well as all corresponding scoring results, to allow for external validation and reproducibility.</abstract>
<identifier type="citekey">kocmi-federmann-2023-large</identifier>
<location>
<url>https://aclanthology.org/2023.eamt-1.19</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>193</start>
<end>203</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Language Models Are State-of-the-Art Evaluators of Translation Quality
%A Kocmi, Tom
%A Federmann, Christian
%Y Nurminen, Mary
%Y Brenner, Judith
%Y Koponen, Maarit
%Y Latomaa, Sirkku
%Y Mikhailov, Mikhail
%Y Schierl, Frederike
%Y Ranasinghe, Tharindu
%Y Vanmassenhove, Eva
%Y Vidal, Sergi Alvarez
%Y Aranberri, Nora
%Y Nunziatini, Mara
%Y Escartín, Carla Parra
%Y Forcada, Mikel
%Y Popovic, Maja
%Y Scarton, Carolina
%Y Moniz, Helena
%S Proceedings of the 24th Annual Conference of the European Association for Machine Translation
%D 2023
%8 June
%I European Association for Machine Translation
%C Tampere, Finland
%F kocmi-federmann-2023-large
%X We describe GEMBA, a GPT-based metric for assessment of translation quality, which works both with a reference translation and without. In our evaluation, we focus on zero-shot prompting, comparing four prompt variants in two modes, based on the availability of the reference. We investigate seven versions of GPT models, including ChatGPT. We show that our method for translation quality assessment only works with GPT 3.5 and larger models. Comparing to results from WMT22’s Metrics shared task, our method achieves state-of-the-art accuracy in both modes when compared to MQM-based human labels. Our results are valid on the system level for all three WMT22 Metrics shared task language pairs, namely English into German, English into Russian, and Chinese into English. This provides a first glimpse into the usefulness of pre-trained, generative large language models for quality assessment of translations. We publicly release all our code and prompt templates used for the experiments described in this work, as well as all corresponding scoring results, to allow for external validation and reproducibility.
%U https://aclanthology.org/2023.eamt-1.19
%P 193-203
Markdown (Informal)
[Large Language Models Are State-of-the-Art Evaluators of Translation Quality](https://aclanthology.org/2023.eamt-1.19) (Kocmi & Federmann, EAMT 2023)
ACL