<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raghaw-etal-2026-cliq">
    <titleInfo>
        <title>CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual–Textual Alignment for QA-Style Radiology Report Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chandravardhan</namePart>
        <namePart type="given">Singh</namePart>
        <namePart type="family">Raghaw</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shahid</namePart>
        <namePart type="given">Shafi</namePart>
        <namePart type="family">Dar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arnav</namePart>
        <namePart type="given">Nishith</namePart>
        <namePart type="family">Sharma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shrey</namePart>
        <namePart type="family">Modi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nagendra</namePart>
        <namePart type="family">Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Radiology reports are essential for diagnostic reasoning and patient care, yet their manual preparation is time-consuming and cognitively demanding. Automatic radiology report generation (RRG) offers a scalable alternative, but existing models often produce lengthy, unstructured narratives that overlook diagnostic cues and multi-view information. We present Clinical-Knowledge Guided Disease-aware Visual–Textual Alignment for QA-Style Radiology Report Generation (CliQ-RRG), a unified two-stage framework for interpretable and clinically grounded reporting. In Stage 1, CliQ-RRG employs a Disease-aware Visual–Textual Alignment module that aligns image and text representations using predicted disease embeddings, reinforced by a Prior-Guided Attention Module (PrAM) to capture multi-view dependencies across current and prior scans. In Stage 2, GraphRAG-guided retrieval augments intermediate textual representations with graph-grounded clinical evidence, and a large language model restructures them into concise, interpretable question–answer (QA) pairs with diagnostic summaries. Experiments on two public chest X-ray benchmarks demonstrate that CliQ-RRG consistently outperforms prior methods across both lexical and clinical metrics, generating accurate and clinically coherent QA-style radiology reports. Code is available at https://github.com/chandravardhan-singh-raghaw/CliQ-RRG.</abstract>
    <identifier type="citekey">raghaw-etal-2026-cliq</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.2333</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2333/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>50153</start>
            <end>50171</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual–Textual Alignment for QA-Style Radiology Report Generation
%A Raghaw, Chandravardhan Singh
%A Dar, Shahid Shafi
%A Sharma, Arnav Nishith
%A Modi, Shrey
%A Kumar, Nagendra
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F raghaw-etal-2026-cliq
%X Radiology reports are essential for diagnostic reasoning and patient care, yet their manual preparation is time-consuming and cognitively demanding. Automatic radiology report generation (RRG) offers a scalable alternative, but existing models often produce lengthy, unstructured narratives that overlook diagnostic cues and multi-view information. We present Clinical-Knowledge Guided Disease-aware Visual–Textual Alignment for QA-Style Radiology Report Generation (CliQ-RRG), a unified two-stage framework for interpretable and clinically grounded reporting. In Stage 1, CliQ-RRG employs a Disease-aware Visual–Textual Alignment module that aligns image and text representations using predicted disease embeddings, reinforced by a Prior-Guided Attention Module (PrAM) to capture multi-view dependencies across current and prior scans. In Stage 2, GraphRAG-guided retrieval augments intermediate textual representations with graph-grounded clinical evidence, and a large language model restructures them into concise, interpretable question–answer (QA) pairs with diagnostic summaries. Experiments on two public chest X-ray benchmarks demonstrate that CliQ-RRG consistently outperforms prior methods across both lexical and clinical metrics, generating accurate and clinically coherent QA-style radiology reports. Code is available at https://github.com/chandravardhan-singh-raghaw/CliQ-RRG.
%R 10.18653/2026.findings-emnlp.2333
%U https://aclanthology.org/2026.findings-emnlp.2333/
%U https://doi.org/10.18653/2026.findings-emnlp.2333
%P 50153-50171

Markdown (Informal)

[CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual–Textual Alignment for QA-Style Radiology Report Generation](https://aclanthology.org/2026.findings-emnlp.2333/) (Raghaw et al., Findings 2026)

• CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual–Textual Alignment for QA-Style Radiology Report Generation (Raghaw et al., Findings 2026)

ACL

• Chandravardhan Singh Raghaw, Shahid Shafi Dar, Arnav Nishith Sharma, Shrey Modi, and Nagendra Kumar. 2026. CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual–Textual Alignment for QA-Style Radiology Report Generation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 50153–50171, Budapest, Hungary. Association for Computational Linguistics.