<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nourbakhsh-etal-2026-medprob">
    <titleInfo>
        <title>MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Erfan</namePart>
        <namePart type="family">Nourbakhsh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ke</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anthony</namePart>
        <namePart type="family">Rios</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>Medical visual question answering (Med-VQA) is often assumed to require medical fine-tuning, large models, or complex multi-agent pipelines. We revisit this assumption with MedProb, a lightweight probing framework that predicts multiple-choice Med-VQA answers from frozen VLM representations without free-text generation. Across PATH-VQA, SLAKE, and VQA-RAD, MedProb recovers substantially more answer-relevant signal than prompting and performs stronger than medical VLMs and agentic systems. Probing also reduces the apparent gap between small and large models compared to prompting, suggesting that smaller VLMs contain more recoverable Med-VQA signal than generation-based evaluation reveals. Across 14 matched general-purpose and medical VLM pairs, medical adaptation does not consistently improve this linear decodability.</abstract>
    <identifier type="citekey">nourbakhsh-etal-2026-medprob</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1320</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1320/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>27961</start>
            <end>27999</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering
%A Nourbakhsh, Erfan
%A Yang, Ke
%A Rios, Anthony
%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 nourbakhsh-etal-2026-medprob
%X Medical visual question answering (Med-VQA) is often assumed to require medical fine-tuning, large models, or complex multi-agent pipelines. We revisit this assumption with MedProb, a lightweight probing framework that predicts multiple-choice Med-VQA answers from frozen VLM representations without free-text generation. Across PATH-VQA, SLAKE, and VQA-RAD, MedProb recovers substantially more answer-relevant signal than prompting and performs stronger than medical VLMs and agentic systems. Probing also reduces the apparent gap between small and large models compared to prompting, suggesting that smaller VLMs contain more recoverable Med-VQA signal than generation-based evaluation reveals. Across 14 matched general-purpose and medical VLM pairs, medical adaptation does not consistently improve this linear decodability.
%R 10.18653/2026.findings-emnlp.1320
%U https://aclanthology.org/2026.findings-emnlp.1320/
%U https://doi.org/10.18653/2026.findings-emnlp.1320
%P 27961-27999

Markdown (Informal)

[MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering](https://aclanthology.org/2026.findings-emnlp.1320/) (Nourbakhsh et al., Findings 2026)

• MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering (Nourbakhsh et al., Findings 2026)

ACL

• Erfan Nourbakhsh, Ke Yang, and Anthony Rios. 2026. MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 27961–27999, Budapest, Hungary. Association for Computational Linguistics.