<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pavlova-makhlouf-2026-mosaic">
    <titleInfo>
        <title>MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning</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>
    <name type="personal">
        <namePart type="given">Mohammed</namePart>
        <namePart type="family">Makhlouf</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>We introduce MOSAIC (Masked Objective with Selective Adaptation for In-domain Contrastive learning), a multi-stage framework for domain adaptation of text embedding models that incorporates joint domain-specific masked supervision. Our approach addresses the challenges of adapting large-scale general-domain text embedding models to specialized domains. By jointly optimizing masked language modeling (MLM) and contrastive objectives within a unified training pipeline, our method enables effective learning of domain-relevant representations while preserving the robust semantic discrimination properties of the original model. We empirically validate our approach on both high-resource and low-resource domains, achieving improvements up to 13.4% in NDCG@10 (Normalized Discounted Cumulative Gain) over strong general-domain baselines. Comprehensive ablation studies further demonstrate the effectiveness of each component, highlighting the importance of balanced joint supervision and staged adaptation.</abstract>
    <identifier type="citekey">pavlova-makhlouf-2026-mosaic</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.197/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>3792</start>
            <end>3807</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning
%A Pavlova, Vera
%A Makhlouf, Mohammed
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F pavlova-makhlouf-2026-mosaic
%X We introduce MOSAIC (Masked Objective with Selective Adaptation for In-domain Contrastive learning), a multi-stage framework for domain adaptation of text embedding models that incorporates joint domain-specific masked supervision. Our approach addresses the challenges of adapting large-scale general-domain text embedding models to specialized domains. By jointly optimizing masked language modeling (MLM) and contrastive objectives within a unified training pipeline, our method enables effective learning of domain-relevant representations while preserving the robust semantic discrimination properties of the original model. We empirically validate our approach on both high-resource and low-resource domains, achieving improvements up to 13.4% in NDCG@10 (Normalized Discounted Cumulative Gain) over strong general-domain baselines. Comprehensive ablation studies further demonstrate the effectiveness of each component, highlighting the importance of balanced joint supervision and staged adaptation.
%U https://aclanthology.org/2026.findings-eacl.197/
%P 3792-3807

Markdown (Informal)

[MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning](https://aclanthology.org/2026.findings-eacl.197/) (Pavlova & Makhlouf, Findings 2026)

• MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning (Pavlova & Makhlouf, Findings 2026)

ACL

• Vera Pavlova and Mohammed Makhlouf. 2026. MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning. In Findings of the Association for Computational Linguistics: EACL 2026, pages 3792–3807, Rabat, Morocco. Association for Computational Linguistics.