<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmad-etal-2026-dr">
    <titleInfo>
        <title>DR-RAG: Addressing Retrieval Misalignment in Low-Resource Urdu Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Saad</namePart>
        <namePart type="family">Ahmad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="family">Hammad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="family">Zeeshan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Faizad</namePart>
        <namePart type="family">Ullah</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Asim</namePart>
        <namePart type="family">Karim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kengatharaiyer</namePart>
            <namePart type="family">Sarveswaran</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ashwini</namePart>
            <namePart type="family">Vaidya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Retrieval-Augmented Generation performs well on English QA benchmarks, but degrades considerably in morphologically rich, low-resource languages. Urdu presents a particularly challenging case: heavy inflectional morphology, Nastaliq script inconsistencies, and limited training data produce a systematic mismatch between query representations and indexed document content that standard retrieval architectures cannot bridge. We propose DR-RAG (Dual-Representation Retrieval-Augmented Generation), which addresses this through dual indexing. Each document is represented as overlapping text chunks and as automatically generated question-answer pairs. Queries are first matched against the QA index, which aligns more reliably with natural query phrasing than declarative document chunks. When retrieval confidence falls below \ensuremathτ = 0.80, the system falls back to chunk-based retrieval, maintaining coverage without sacrificing precision. Evaluated on Urdu UQA and English SQuAD 2.0, DR-RAG improves Urdu METEOR by 38×, ROUGE-1 by 140%, and reduces generation latency by 43%. LLM-as judge scores show higher faithfulness (3.03 vs 1.93) and overall quality (2.99 vs 2.21) over MultiVector. English performance remains competitive throughout. These results indicate that representation-level alignment between queries and indexed content, rather than increased model complexity, is the critical factor for reliable retrieval in underserved South Asian languages.</abstract>
    <identifier type="citekey">ahmad-etal-2026-dr</identifier>
    <identifier type="doi">10.63317/4wwyss5zkwxs</identifier>
    <location>
        <url>https://aclanthology.org/2026.chipsal-1.6/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>49</start>
            <end>58</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DR-RAG: Addressing Retrieval Misalignment in Low-Resource Urdu Question Answering
%A Ahmad, Saad
%A Hammad, Muhammad
%A Zeeshan, Muhammad
%A Ullah, Faizad
%A Karim, Asim
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%S Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F ahmad-etal-2026-dr
%X Retrieval-Augmented Generation performs well on English QA benchmarks, but degrades considerably in morphologically rich, low-resource languages. Urdu presents a particularly challenging case: heavy inflectional morphology, Nastaliq script inconsistencies, and limited training data produce a systematic mismatch between query representations and indexed document content that standard retrieval architectures cannot bridge. We propose DR-RAG (Dual-Representation Retrieval-Augmented Generation), which addresses this through dual indexing. Each document is represented as overlapping text chunks and as automatically generated question-answer pairs. Queries are first matched against the QA index, which aligns more reliably with natural query phrasing than declarative document chunks. When retrieval confidence falls below \ensuremathτ = 0.80, the system falls back to chunk-based retrieval, maintaining coverage without sacrificing precision. Evaluated on Urdu UQA and English SQuAD 2.0, DR-RAG improves Urdu METEOR by 38×, ROUGE-1 by 140%, and reduces generation latency by 43%. LLM-as judge scores show higher faithfulness (3.03 vs 1.93) and overall quality (2.99 vs 2.21) over MultiVector. English performance remains competitive throughout. These results indicate that representation-level alignment between queries and indexed content, rather than increased model complexity, is the critical factor for reliable retrieval in underserved South Asian languages.
%R 10.63317/4wwyss5zkwxs
%U https://aclanthology.org/2026.chipsal-1.6/
%U https://doi.org/10.63317/4wwyss5zkwxs
%P 49-58

Markdown (Informal)

[DR-RAG: Addressing Retrieval Misalignment in Low-Resource Urdu Question Answering](https://aclanthology.org/2026.chipsal-1.6/) (Ahmad et al., CHiPSAL 2026)

• DR-RAG: Addressing Retrieval Misalignment in Low-Resource Urdu Question Answering (Ahmad et al., CHiPSAL 2026)

ACL

• Saad Ahmad, Muhammad Hammad, Muhammad Zeeshan, Faizad Ullah, and Asim Karim. 2026. DR-RAG: Addressing Retrieval Misalignment in Low-Resource Urdu Question Answering. In Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026), pages 49–58, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).