@inproceedings{elfqih-monti-2024-large,
title = "Large Language Models as Legal Translators of {A}rabic Legislatives: Does {C}hat{GPT} and Gemini Care for Context and Terminology?",
author = "ElFqih, Khadija and
Monti, Johanna",
editor = "Habash, Nizar and
Bouamor, Houda and
Eskander, Ramy and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Abdelali, Ahmed and
Touileb, Samia and
Hamed, Injy and
Onaizan, Yaser and
Alhafni, Bashar and
Antoun, Wissam and
Khalifa, Salam and
Haddad, Hatem and
Zitouni, Imed and
AlKhamissi, Badr and
Almatham, Rawan and
Mrini, Khalil",
booktitle = "Proceedings of The Second Arabic Natural Language Processing Conference",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.arabicnlp-1.10",
doi = "10.18653/v1/2024.arabicnlp-1.10",
pages = "111--122",
abstract = "Accurate translation of terminology and adaptation to in-context information is a pillar to high quality translation. Recently, there is a remarkable interest towards the use and the evaluation of Large Language Models (LLMs) particularly for Machine Translation tasks. Nevertheless, despite their recent advancement and ability to understand and generate human-like language, these LLMs are still far from perfect, especially in domain-specific scenarios, and need to be thoroughly investigated. This is particularly evident in automatically translating legal terminology from Arabic into English and French, where, beyond the inherent complexities of legal language and specialised translations, technical limitations of LLMs further hinder accurate generation of text. In this paper, we present a preliminary evaluation of two evolving LLMs, namely GPT-4 Generative Pre-trained Transformer and Gemini, as legal translators of Arabic legislatives to test their accuracy and the extent to which they care for context and terminology across two language pairs (AR→EN / AR→FR). The study targets the evaluation of Zero-Shot prompting for in-context and out-of-context scenarios of both models relying on a gold standard dataset, verified by professional translators who are also experts in the field. We evaluate the results applying the Multidimensional Quality Metrics to classify translation errors. Moreover, we also evaluate the general LLMs outputs to verify their correctness, consistency, and completeness.In general, our results show that the models are far from perfect and recall for more fine-tuning efforts using specialised terminological data in the legal domain from Arabic into English and French.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elfqih-monti-2024-large">
<titleInfo>
<title>Large Language Models as Legal Translators of Arabic Legislatives: Does ChatGPT and Gemini Care for Context and Terminology?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khadija</namePart>
<namePart type="family">ElFqih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Monti</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>Proceedings of The Second Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Accurate translation of terminology and adaptation to in-context information is a pillar to high quality translation. Recently, there is a remarkable interest towards the use and the evaluation of Large Language Models (LLMs) particularly for Machine Translation tasks. Nevertheless, despite their recent advancement and ability to understand and generate human-like language, these LLMs are still far from perfect, especially in domain-specific scenarios, and need to be thoroughly investigated. This is particularly evident in automatically translating legal terminology from Arabic into English and French, where, beyond the inherent complexities of legal language and specialised translations, technical limitations of LLMs further hinder accurate generation of text. In this paper, we present a preliminary evaluation of two evolving LLMs, namely GPT-4 Generative Pre-trained Transformer and Gemini, as legal translators of Arabic legislatives to test their accuracy and the extent to which they care for context and terminology across two language pairs (AR→EN / AR→FR). The study targets the evaluation of Zero-Shot prompting for in-context and out-of-context scenarios of both models relying on a gold standard dataset, verified by professional translators who are also experts in the field. We evaluate the results applying the Multidimensional Quality Metrics to classify translation errors. Moreover, we also evaluate the general LLMs outputs to verify their correctness, consistency, and completeness.In general, our results show that the models are far from perfect and recall for more fine-tuning efforts using specialised terminological data in the legal domain from Arabic into English and French.</abstract>
<identifier type="citekey">elfqih-monti-2024-large</identifier>
<identifier type="doi">10.18653/v1/2024.arabicnlp-1.10</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.10</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>111</start>
<end>122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Language Models as Legal Translators of Arabic Legislatives: Does ChatGPT and Gemini Care for Context and Terminology?
%A ElFqih, Khadija
%A Monti, Johanna
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Eskander, Ramy
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Abdelali, Ahmed
%Y Touileb, Samia
%Y Hamed, Injy
%Y Onaizan, Yaser
%Y Alhafni, Bashar
%Y Antoun, Wissam
%Y Khalifa, Salam
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Mrini, Khalil
%S Proceedings of The Second Arabic Natural Language Processing Conference
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F elfqih-monti-2024-large
%X Accurate translation of terminology and adaptation to in-context information is a pillar to high quality translation. Recently, there is a remarkable interest towards the use and the evaluation of Large Language Models (LLMs) particularly for Machine Translation tasks. Nevertheless, despite their recent advancement and ability to understand and generate human-like language, these LLMs are still far from perfect, especially in domain-specific scenarios, and need to be thoroughly investigated. This is particularly evident in automatically translating legal terminology from Arabic into English and French, where, beyond the inherent complexities of legal language and specialised translations, technical limitations of LLMs further hinder accurate generation of text. In this paper, we present a preliminary evaluation of two evolving LLMs, namely GPT-4 Generative Pre-trained Transformer and Gemini, as legal translators of Arabic legislatives to test their accuracy and the extent to which they care for context and terminology across two language pairs (AR→EN / AR→FR). The study targets the evaluation of Zero-Shot prompting for in-context and out-of-context scenarios of both models relying on a gold standard dataset, verified by professional translators who are also experts in the field. We evaluate the results applying the Multidimensional Quality Metrics to classify translation errors. Moreover, we also evaluate the general LLMs outputs to verify their correctness, consistency, and completeness.In general, our results show that the models are far from perfect and recall for more fine-tuning efforts using specialised terminological data in the legal domain from Arabic into English and French.
%R 10.18653/v1/2024.arabicnlp-1.10
%U https://aclanthology.org/2024.arabicnlp-1.10
%U https://doi.org/10.18653/v1/2024.arabicnlp-1.10
%P 111-122
Markdown (Informal)
[Large Language Models as Legal Translators of Arabic Legislatives: Does ChatGPT and Gemini Care for Context and Terminology?](https://aclanthology.org/2024.arabicnlp-1.10) (ElFqih & Monti, ArabicNLP-WS 2024)
ACL