<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-fussell-2026-output">
    <titleInfo>
        <title>From Output Metrics to Cognitive Process: Disfluency and Lexical Entrainment for Evaluating Real-Time AI-Mediated Communication</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wanqing</namePart>
        <namePart type="given">Psyche</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Susan</namePart>
        <namePart type="family">Fussell</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 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Esam</namePart>
            <namePart type="family">Ghaleb</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ece</namePart>
            <namePart type="family">Takmaz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Diego</namePart>
            <namePart type="family">Frassinelli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bulat</namePart>
            <namePart type="family">Khaertdinov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Raquel</namePart>
            <namePart type="family">Fernández</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zerrin</namePart>
            <namePart type="family">Yumak</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Asli</namePart>
            <namePart type="family">Ozyurek</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">979-8-89176-482-8</identifier>
    </relatedItem>
    <abstract>Real-time communication mediated by artificial intelligence (AI) can produce an accurate output while changing how a speaker plans an utterance and what a listener receives. Output measures, such as word error rate, machine translation scores, and task accuracy, leave these process effects unobserved. We propose a dual-axis framework that aligns disfluency measures with suggestion correspondence, including lexical entrainment and semantic similarity. Disfluency type, rate, timing, and duration characterize observable production difficulty. Correspondence measures characterize whether suggestion content appears in the response. Observing both axes within the same episode distinguishes behavioral configurations that either family alone leaves ambiguous and supports explicit hypotheses about planning, uptake, and resistance. An illustrative corpus demonstrates event-detection feasibility and shows that semantic correspondence varies with coded incorporation and exceeds a comparison matched on presentation format. These checks leave cognitive interpretations open to experimental validation. We also derive a prediction concerning listeners: removing natural disfluencies may remove cues that listeners use to anticipate difficult or novel material. The resulting framework and reporting protocol extend standard evaluation to the human processes through which real-time AI-mediated communication succeeds or fails.</abstract>
    <identifier type="citekey">he-fussell-2026-output</identifier>
    <location>
        <url>https://aclanthology.org/2026.mint-1.2/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>10</start>
            <end>21</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From Output Metrics to Cognitive Process: Disfluency and Lexical Entrainment for Evaluating Real-Time AI-Mediated Communication
%A He, Wanqing Psyche
%A Fussell, Susan
%Y Ghaleb, Esam
%Y Takmaz, Ece
%Y Frassinelli, Diego
%Y Khaertdinov, Bulat
%Y Fernández, Raquel
%Y Yumak, Zerrin
%Y Ozyurek, Asli
%S Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-482-8
%F he-fussell-2026-output
%X Real-time communication mediated by artificial intelligence (AI) can produce an accurate output while changing how a speaker plans an utterance and what a listener receives. Output measures, such as word error rate, machine translation scores, and task accuracy, leave these process effects unobserved. We propose a dual-axis framework that aligns disfluency measures with suggestion correspondence, including lexical entrainment and semantic similarity. Disfluency type, rate, timing, and duration characterize observable production difficulty. Correspondence measures characterize whether suggestion content appears in the response. Observing both axes within the same episode distinguishes behavioral configurations that either family alone leaves ambiguous and supports explicit hypotheses about planning, uptake, and resistance. An illustrative corpus demonstrates event-detection feasibility and shows that semantic correspondence varies with coded incorporation and exceeds a comparison matched on presentation format. These checks leave cognitive interpretations open to experimental validation. We also derive a prediction concerning listeners: removing natural disfluencies may remove cues that listeners use to anticipate difficult or novel material. The resulting framework and reporting protocol extend standard evaluation to the human processes through which real-time AI-mediated communication succeeds or fails.
%U https://aclanthology.org/2026.mint-1.2/
%P 10-21

Markdown (Informal)

[From Output Metrics to Cognitive Process: Disfluency and Lexical Entrainment for Evaluating Real-Time AI-Mediated Communication](https://aclanthology.org/2026.mint-1.2/) (He & Fussell, MINT 2026)

• From Output Metrics to Cognitive Process: Disfluency and Lexical Entrainment for Evaluating Real-Time AI-Mediated Communication (He & Fussell, MINT 2026)

ACL

• Wanqing Psyche He and Susan Fussell. 2026. From Output Metrics to Cognitive Process: Disfluency and Lexical Entrainment for Evaluating Real-Time AI-Mediated Communication. In Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue, pages 10–21, Budapest, Hungary. Association for Computational Linguistics.