<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pavlova-2025-multi">
    <titleInfo>
        <title>Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vera</namePart>
        <namePart type="family">Pavlova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the New Horizons in Computational Linguistics for Religious Texts</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sane</namePart>
            <namePart type="family">Yagi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Majdi</namePart>
            <namePart type="family">Sawalha</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bayan</namePart>
            <namePart type="given">Abu</namePart>
            <namePart type="family">Shawar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abdallah</namePart>
            <namePart type="given">T</namePart>
            <namePart type="family">AlShdaifat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Norhan</namePart>
            <namePart type="family">Abbas</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name>
            <namePart>Organizers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This study examines the use of Natural Language Processing (NLP) technology within the Islamic domain, focusing on developing an Islamic neural retrieval model. By leveraging the robust XLM-R base model, the research employs a language reduction technique to create a lightweight bilingual large language model (LLM). Our approach for domain adaptation addresses the unique challenges faced in the Islamic domain, where substantial in-domain corpora exist only in Arabic while limited in other languages, including English. The work utilizes a multi-stage training process for retrieval models, incorporating large retrieval datasets, such as MS MARCO, and smaller, in-domain datasets to improve retrieval performance. Additionally, we have curated an in-domain retrieval dataset in English by employing data augmentation techniques and involving a reliable Islamic source. This approach enhances the domain-specific dataset for retrieval, leading to further performance gains. The findings suggest that combining domain adaptation and a multi-stage training method for the bilingual Islamic neural retrieval model enables it to outperform monolingual models on downstream retrieval tasks.</abstract>
    <identifier type="citekey">pavlova-2025-multi</identifier>
    <location>
        <url>https://aclanthology.org/2025.clrel-1.4/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>42</start>
            <end>52</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval
%A Pavlova, Vera
%Y Yagi, Sane
%Y Sawalha, Majdi
%Y Shawar, Bayan Abu
%Y AlShdaifat, Abdallah T.
%Y Abbas, Norhan
%E Organizers
%S Proceedings of the New Horizons in Computational Linguistics for Religious Texts
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F pavlova-2025-multi
%X This study examines the use of Natural Language Processing (NLP) technology within the Islamic domain, focusing on developing an Islamic neural retrieval model. By leveraging the robust XLM-R base model, the research employs a language reduction technique to create a lightweight bilingual large language model (LLM). Our approach for domain adaptation addresses the unique challenges faced in the Islamic domain, where substantial in-domain corpora exist only in Arabic while limited in other languages, including English. The work utilizes a multi-stage training process for retrieval models, incorporating large retrieval datasets, such as MS MARCO, and smaller, in-domain datasets to improve retrieval performance. Additionally, we have curated an in-domain retrieval dataset in English by employing data augmentation techniques and involving a reliable Islamic source. This approach enhances the domain-specific dataset for retrieval, leading to further performance gains. The findings suggest that combining domain adaptation and a multi-stage training method for the bilingual Islamic neural retrieval model enables it to outperform monolingual models on downstream retrieval tasks.
%U https://aclanthology.org/2025.clrel-1.4/
%P 42-52

Markdown (Informal)

[Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval](https://aclanthology.org/2025.clrel-1.4/) (Pavlova, CLRel 2025)

• Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval (Pavlova, CLRel 2025)

ACL

• Vera Pavlova. 2025. Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval. In Proceedings of the New Horizons in Computational Linguistics for Religious Texts, pages 42–52, Abu Dhabi, UAE. Association for Computational Linguistics.