<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mudryi-laba-2025-benchmark">
    <titleInfo>
        <title>From Benchmark to Better Embeddings: Leveraging Synonym Substitution to Enhance Multimodal Models in Ukrainian</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Volodymyr</namePart>
        <namePart type="family">Mudryi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yurii</namePart>
        <namePart type="family">Laba</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>We study the robustness of text–image retrieval for Ukrainian under synonym-substitution attacks (SSA). On Multi30K with OpenCLIP, we evaluate two SSA methods: dictionary-based and LLM-based, and find Ukrainian degrades far more than English (e.g., GPT-4o SSA drops HIT@1 from 32.1 ࢐ 10.9 vs. 41.6 ࢐ 30.4). We introduce a Hybrid method that filters dictionary candidates with an LLM to preserve sense and grammar, yielding higher-quality perturbations (Ukrainian HIT@1 16.8 vs. 7.6/10.9). To mitigate this problem, we propose synonym-augmented fine-tuning, injecting one-word substitutions into training; it boosts robustness (Hybrid 28.1, GPT-4o 25.1) without harming original performance. This is the first systematic SSA evaluation for Ukrainian multimodal retrieval and a practical recipe for improving models in low-resource, morphologically rich languages. We release code, prompts, and trained checkpoints at https://github.com/YuriiLaba/UA-B2BE.</abstract>
    <identifier type="citekey">mudryi-laba-2025-benchmark</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.1115/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>20458</start>
            <end>20468</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From Benchmark to Better Embeddings: Leveraging Synonym Substitution to Enhance Multimodal Models in Ukrainian
%A Mudryi, Volodymyr
%A Laba, Yurii
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F mudryi-laba-2025-benchmark
%X We study the robustness of text–image retrieval for Ukrainian under synonym-substitution attacks (SSA). On Multi30K with OpenCLIP, we evaluate two SSA methods: dictionary-based and LLM-based, and find Ukrainian degrades far more than English (e.g., GPT-4o SSA drops HIT@1 from 32.1 ࢐ 10.9 vs. 41.6 ࢐ 30.4). We introduce a Hybrid method that filters dictionary candidates with an LLM to preserve sense and grammar, yielding higher-quality perturbations (Ukrainian HIT@1 16.8 vs. 7.6/10.9). To mitigate this problem, we propose synonym-augmented fine-tuning, injecting one-word substitutions into training; it boosts robustness (Hybrid 28.1, GPT-4o 25.1) without harming original performance. This is the first systematic SSA evaluation for Ukrainian multimodal retrieval and a practical recipe for improving models in low-resource, morphologically rich languages. We release code, prompts, and trained checkpoints at https://github.com/YuriiLaba/UA-B2BE.
%U https://aclanthology.org/2025.findings-emnlp.1115/
%P 20458-20468

Markdown (Informal)

[From Benchmark to Better Embeddings: Leveraging Synonym Substitution to Enhance Multimodal Models in Ukrainian](https://aclanthology.org/2025.findings-emnlp.1115/) (Mudryi & Laba, Findings 2025)

• From Benchmark to Better Embeddings: Leveraging Synonym Substitution to Enhance Multimodal Models in Ukrainian (Mudryi & Laba, Findings 2025)

ACL

• Volodymyr Mudryi and Yurii Laba. 2025. From Benchmark to Better Embeddings: Leveraging Synonym Substitution to Enhance Multimodal Models in Ukrainian. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 20458–20468, Suzhou, China. Association for Computational Linguistics.