<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="srinivasan-etal-2026-recap">
    <titleInfo>
        <title>RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adarsh</namePart>
        <namePart type="family">Srinivasan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jacob</namePart>
        <namePart type="family">Dineen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="given">Uzair</namePart>
        <namePart type="family">Sarfraz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="given">Umar</namePart>
        <namePart type="family">Afzal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Irbaz</namePart>
        <namePart type="family">Riaz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ben</namePart>
        <namePart type="family">Zhou</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 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Asma</namePart>
            <namePart type="family">Ben Abacha</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Danielle</namePart>
            <namePart type="family">Bitterman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tristan</namePart>
            <namePart type="family">Naumann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kirk</namePart>
            <namePart type="family">Roberts</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large language models in healthcare often produce emotionally flat or opaque responses, failing to provide the transparent reasoning required for clinical trust. We present RECAP (Reflect–Extract–Calibrate–Align–Produce), an inference-time framework grounded in cognitive appraisal theory that decomposes patient input into auditable, appraisal-theoretic stages without retraining. Across multiple benchmarks and models from 8B to 120B parameters, RECAP improves alignment with human judgments, with gains inversely proportional to model scale. Intermediate outputs further reveal that models systematically underweight relational factors such as social support. In blinded evaluations, oncology fellows rated RECAP responses significantly higher than baselines with 76–88% win rates, demonstrating that principled prompting can enhance medical AI’s emotional intelligence while maintaining the transparency required for clinical deployment.</abstract>
    <identifier type="citekey">srinivasan-etal-2026-recap</identifier>
    <identifier type="doi">10.63317/5epg4xxjjygt</identifier>
    <location>
        <url>https://aclanthology.org/2026.clinicalnlp-1.38/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>350</start>
            <end>368</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems
%A Srinivasan, Adarsh
%A Dineen, Jacob
%A Sarfraz, Muhammad Uzair
%A Afzal, Muhammad Umar
%A Riaz, Irbaz
%A Zhou, Ben
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F srinivasan-etal-2026-recap
%X Large language models in healthcare often produce emotionally flat or opaque responses, failing to provide the transparent reasoning required for clinical trust. We present RECAP (Reflect–Extract–Calibrate–Align–Produce), an inference-time framework grounded in cognitive appraisal theory that decomposes patient input into auditable, appraisal-theoretic stages without retraining. Across multiple benchmarks and models from 8B to 120B parameters, RECAP improves alignment with human judgments, with gains inversely proportional to model scale. Intermediate outputs further reveal that models systematically underweight relational factors such as social support. In blinded evaluations, oncology fellows rated RECAP responses significantly higher than baselines with 76–88% win rates, demonstrating that principled prompting can enhance medical AI’s emotional intelligence while maintaining the transparency required for clinical deployment.
%R 10.63317/5epg4xxjjygt
%U https://aclanthology.org/2026.clinicalnlp-1.38/
%U https://doi.org/10.63317/5epg4xxjjygt
%P 350-368

Markdown (Informal)

[RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems](https://aclanthology.org/2026.clinicalnlp-1.38/) (Srinivasan et al., ClinicalNLP 2026)

• RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems (Srinivasan et al., ClinicalNLP 2026)

ACL

• Adarsh Srinivasan, Jacob Dineen, Muhammad Uzair Sarfraz, Muhammad Umar Afzal, Irbaz Riaz, and Ben Zhou. 2026. RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems. In Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026, pages 350–368, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).