<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2026-medf2route">
    <titleInfo>
        <title>MedF²Route: Evidence-Routed Graph Verification for Hallucination Detection in Clinical LVLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiao</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruiying</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haonan</namePart>
        <namePart type="family">Qin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianyuan</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuqi</namePart>
        <namePart type="family">Fang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Caifeng</namePart>
        <namePart type="family">Shan</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Hallucination detection in clinical large vision-language models requires cross-verifying heterogeneous evidence, including patient text and images for faithfulness, and medical knowledge for factuality. However, existing pipelines either verify these dimensions in isolation or conflate them into a uniform process, potentially causing evidence misalignment that limits detection precision. Consequently, we posit that the essence of black-box hallucination detection is an evidence routing problem and propose MedF²Route, an Evidence-Routed Graph Verification Framework for both Faithfulness and Factuality hallucination detection. Specifically, it first transforms free-text clinical queries and model responses into structured graphs, partitioning the response graph into independent subgraphs to separate patient-specific grounding from knowledge-based diagnostic inference. An evidence-aware routing and verification mechanism then dynamically dispatches response triplets in these subgraphs to their dedicated heterogeneous evidence sources for targeted verification. Experiments on our MedF²Bench diagnostic benchmark show that our framework outperforms state-of-the-art baselines, notably improving detection precision. Overall, MedF²Route enables professional and precise detection of clinical hallucinations, underpinning the trustworthiness of clinical LVLMs. The code and data are available at https://github.com/Agentic-CliniAI/MedF2Route.</abstract>
    <identifier type="citekey">song-etal-2026-medf2route</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1152/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>26415</start>
            <end>26438</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MedF²Route: Evidence-Routed Graph Verification for Hallucination Detection in Clinical LVLMs
%A Song, Xiao
%A Chen, Ruiying
%A Qin, Haonan
%A Huang, Jianyuan
%A Fang, Yuqi
%A Shan, Caifeng
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F song-etal-2026-medf2route
%X Hallucination detection in clinical large vision-language models requires cross-verifying heterogeneous evidence, including patient text and images for faithfulness, and medical knowledge for factuality. However, existing pipelines either verify these dimensions in isolation or conflate them into a uniform process, potentially causing evidence misalignment that limits detection precision. Consequently, we posit that the essence of black-box hallucination detection is an evidence routing problem and propose MedF²Route, an Evidence-Routed Graph Verification Framework for both Faithfulness and Factuality hallucination detection. Specifically, it first transforms free-text clinical queries and model responses into structured graphs, partitioning the response graph into independent subgraphs to separate patient-specific grounding from knowledge-based diagnostic inference. An evidence-aware routing and verification mechanism then dynamically dispatches response triplets in these subgraphs to their dedicated heterogeneous evidence sources for targeted verification. Experiments on our MedF²Bench diagnostic benchmark show that our framework outperforms state-of-the-art baselines, notably improving detection precision. Overall, MedF²Route enables professional and precise detection of clinical hallucinations, underpinning the trustworthiness of clinical LVLMs. The code and data are available at https://github.com/Agentic-CliniAI/MedF2Route.
%U https://aclanthology.org/2026.emnlp-main.1152/
%P 26415-26438

Markdown (Informal)

[MedF2Route: Evidence-Routed Graph Verification for Hallucination Detection in Clinical LVLMs](https://aclanthology.org/2026.emnlp-main.1152/) (Song et al., EMNLP 2026)

• MedF2Route: Evidence-Routed Graph Verification for Hallucination Detection in Clinical LVLMs (Song et al., EMNLP 2026)

ACL

• Xiao Song, Ruiying Chen, Haonan Qin, Jianyuan Huang, Yuqi Fang, and Caifeng Shan. 2026. MedF2Route: Evidence-Routed Graph Verification for Hallucination Detection in Clinical LVLMs. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 26415–26438, Budapest, Hungary. Association for Computational Linguistics.