<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahman-etal-2026-utd">
    <titleInfo>
        <title>UTD-HLTRI at SemEval-2026 Task 7: Bridging Cultural Knowledge Gaps in LLMs via Web-Augmented Context</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="given">Marufur</namePart>
        <namePart type="family">Rahman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rakshitha</namePart>
        <namePart type="given">Rao</namePart>
        <namePart type="family">Ailneni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sanda</namePart>
        <namePart type="family">Harabagiu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Kochmar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai</namePart>
            <namePart type="family">North</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mamoru</namePart>
            <namePart type="family">Komachi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-414-9</identifier>
    </relatedItem>
    <abstract>Though Large Language Models (LLMs) have been serving global users through a wide range of services, concerns remain regarding their cultural bias and misalignment with people of underrepresented communities. Increasing use of LLMs presents significant implications, as they have the potential to influence people’s original values toward a certain cultural perspective. Cultural alignment of LLMs with culture-specific knowledge offers a suitable solution to this concern. In our participation in the Semeval-2026 Task 7 we considered a prompt engineering-based cultural alignment strategy to address the cultural knowledge gap in LLMs. Our approach achieved promising 86.34% accuracy for Japanese culture-relevant multiple-choice questions from the BLEND benchmark.</abstract>
    <identifier type="citekey">rahman-etal-2026-utd</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.335/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>2657</start>
            <end>2663</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T UTD-HLTRI at SemEval-2026 Task 7: Bridging Cultural Knowledge Gaps in LLMs via Web-Augmented Context
%A Rahman, Mohammad Marufur
%A Ailneni, Rakshitha Rao
%A Harabagiu, Sanda
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F rahman-etal-2026-utd
%X Though Large Language Models (LLMs) have been serving global users through a wide range of services, concerns remain regarding their cultural bias and misalignment with people of underrepresented communities. Increasing use of LLMs presents significant implications, as they have the potential to influence people’s original values toward a certain cultural perspective. Cultural alignment of LLMs with culture-specific knowledge offers a suitable solution to this concern. In our participation in the Semeval-2026 Task 7 we considered a prompt engineering-based cultural alignment strategy to address the cultural knowledge gap in LLMs. Our approach achieved promising 86.34% accuracy for Japanese culture-relevant multiple-choice questions from the BLEND benchmark.
%U https://aclanthology.org/2026.semeval-1.335/
%P 2657-2663

Markdown (Informal)

[UTD-HLTRI at SemEval-2026 Task 7: Bridging Cultural Knowledge Gaps in LLMs via Web-Augmented Context](https://aclanthology.org/2026.semeval-1.335/) (Rahman et al., SemEval 2026)

• UTD-HLTRI at SemEval-2026 Task 7: Bridging Cultural Knowledge Gaps in LLMs via Web-Augmented Context (Rahman et al., SemEval 2026)

ACL

• Mohammad Marufur Rahman, Rakshitha Rao Ailneni, and Sanda Harabagiu. 2026. UTD-HLTRI at SemEval-2026 Task 7: Bridging Cultural Knowledge Gaps in LLMs via Web-Augmented Context. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 2657–2663, San Diego, California, USA. Association for Computational Linguistics.