<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oren-etal-2026-generating">
    <titleInfo>
        <title>Generating Clinical Vignettes that Preserve Cognitive Formulations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Amit</namePart>
        <namePart type="family">Oren</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nimrod</namePart>
        <namePart type="family">Hertz-Palmor</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dean</namePart>
        <namePart type="family">Ariel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guy</namePart>
        <namePart type="family">Laban</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>Large language models can generate fluent clinical case vignettes, but fluency alone does not ensure fidelity to a specifiable clinical structure. We introduce FORMA, a theory-grounded framework that compiles a cognitive model of a disorder into a directed weighted graph, samples a person-specific configuration of that graph, and validates whether the generated vignette preserves the specified components and causal links. We instantiate FORMA on Posttraumatic Stress Disorder using the Ehlers and Clark cognitive model, generating 16,500 vignettes across 500 personas, 11 generation models, and three ablation conditions. Evaluation combines an external edge-recovery probe, two clinical experts, a scaled LLM judge, and a clinician user study with 100 licensed practitioners. The cognitive graph is recoverable from full-condition vignettes (MCC = +0.41, AUC = 0.70) but not from zero-shot generation (MCC = +0.01, AUC = 0.50). Experts rate full vignettes substantially higher than zero-shot alternatives, and clinicians perceive them to be human-written 85% of the time, compared with 22% for zero-shot. FORMA also reduces demographic disparity in perceived quality by 1.5–7×. These results show that cognitive formulation can serve as an auditable specification for scalable synthetic clinical text generation. A repository with the data and code is available online: https://github.com/Amit-Oren/FORMA.</abstract>
    <identifier type="citekey">oren-etal-2026-generating</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1384</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1384/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>29423</start>
            <end>29472</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Generating Clinical Vignettes that Preserve Cognitive Formulations
%A Oren, Amit
%A Hertz-Palmor, Nimrod
%A Ariel, Dean
%A Laban, Guy
%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 oren-etal-2026-generating
%X Large language models can generate fluent clinical case vignettes, but fluency alone does not ensure fidelity to a specifiable clinical structure. We introduce FORMA, a theory-grounded framework that compiles a cognitive model of a disorder into a directed weighted graph, samples a person-specific configuration of that graph, and validates whether the generated vignette preserves the specified components and causal links. We instantiate FORMA on Posttraumatic Stress Disorder using the Ehlers and Clark cognitive model, generating 16,500 vignettes across 500 personas, 11 generation models, and three ablation conditions. Evaluation combines an external edge-recovery probe, two clinical experts, a scaled LLM judge, and a clinician user study with 100 licensed practitioners. The cognitive graph is recoverable from full-condition vignettes (MCC = +0.41, AUC = 0.70) but not from zero-shot generation (MCC = +0.01, AUC = 0.50). Experts rate full vignettes substantially higher than zero-shot alternatives, and clinicians perceive them to be human-written 85% of the time, compared with 22% for zero-shot. FORMA also reduces demographic disparity in perceived quality by 1.5–7×. These results show that cognitive formulation can serve as an auditable specification for scalable synthetic clinical text generation. A repository with the data and code is available online: https://github.com/Amit-Oren/FORMA.
%R 10.18653/2026.findings-emnlp.1384
%U https://aclanthology.org/2026.findings-emnlp.1384/
%U https://doi.org/10.18653/2026.findings-emnlp.1384
%P 29423-29472

Markdown (Informal)

[Generating Clinical Vignettes that Preserve Cognitive Formulations](https://aclanthology.org/2026.findings-emnlp.1384/) (Oren et al., Findings 2026)

• Generating Clinical Vignettes that Preserve Cognitive Formulations (Oren et al., Findings 2026)

ACL

• Amit Oren, Nimrod Hertz-Palmor, Dean Ariel, and Guy Laban. 2026. Generating Clinical Vignettes that Preserve Cognitive Formulations. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 29423–29472, Budapest, Hungary. Association for Computational Linguistics.