<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khan-etal-2026-speak">
    <titleInfo>
        <title>Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Muneeb</namePart>
        <namePart type="family">Khan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Frederic</namePart>
        <namePart type="family">Kirstein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Terry</namePart>
        <namePart type="family">Ruas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bela</namePart>
        <namePart type="family">Gipp</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>In online meeting delegation, LLM agents fail to recognize when to speak. With no structured way to track stances, coverage, and floor, they miss the moments where they should contribute. Prompt-only delegates stay silent on 51.4% of the absent participant’s talking opportunities on the AMI corpus. We present CAPA (Collaborative Agent Predictive Architecture), an architecture for online meeting delegation. A Perceiver updates the meeting state from each observed turn. A Predictor forecasts how the conversation will continue. A Controller decides whether to speak and which proposition to surface. A Generator phrases the chosen contribution in the participant’s style. Two judges score the forecast and the action against the next observed turn. A Recalibrator updates the meeting state from those verdicts for future decisions. To evaluate online delegation, we introduce an episode-level protocol that scores whether, when, and what a delegate contributes around the participant’s actual idea units. The protocol’s schema-constrained LLM judges align with human annotations at Cohen’s ąppa = 0.71. On 137 AMI meetings, CAPA reduces the silence rate from 51.4% to 2.5%, doubles credited recovery (26.1 ࢐ 52.2), and keeps hallucination at 0.6%. The failure mode shifts from omission to selection, with each residual near-miss attributable to a specific module of the architecture. Mechanism ablations identify the meeting state as the lever that closes the recognition gap, where raw-context scaling alone does not.</abstract>
    <identifier type="citekey">khan-etal-2026-speak</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1377/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>31446</start>
            <end>31472</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting
%A Khan, Muneeb
%A Kirstein, Frederic
%A Ruas, Terry
%A Gipp, Bela
%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 khan-etal-2026-speak
%X In online meeting delegation, LLM agents fail to recognize when to speak. With no structured way to track stances, coverage, and floor, they miss the moments where they should contribute. Prompt-only delegates stay silent on 51.4% of the absent participant’s talking opportunities on the AMI corpus. We present CAPA (Collaborative Agent Predictive Architecture), an architecture for online meeting delegation. A Perceiver updates the meeting state from each observed turn. A Predictor forecasts how the conversation will continue. A Controller decides whether to speak and which proposition to surface. A Generator phrases the chosen contribution in the participant’s style. Two judges score the forecast and the action against the next observed turn. A Recalibrator updates the meeting state from those verdicts for future decisions. To evaluate online delegation, we introduce an episode-level protocol that scores whether, when, and what a delegate contributes around the participant’s actual idea units. The protocol’s schema-constrained LLM judges align with human annotations at Cohen’s ąppa = 0.71. On 137 AMI meetings, CAPA reduces the silence rate from 51.4% to 2.5%, doubles credited recovery (26.1 ࢐ 52.2), and keeps hallucination at 0.6%. The failure mode shifts from omission to selection, with each residual near-miss attributable to a specific module of the architecture. Mechanism ablations identify the meeting state as the lever that closes the recognition gap, where raw-context scaling alone does not.
%U https://aclanthology.org/2026.emnlp-main.1377/
%P 31446-31472

Markdown (Informal)

[Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting](https://aclanthology.org/2026.emnlp-main.1377/) (Khan et al., EMNLP 2026)

• Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting (Khan et al., EMNLP 2026)

ACL

• Muneeb Khan, Frederic Kirstein, Terry Ruas, and Bela Gipp. 2026. Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 31446–31472, Budapest, Hungary. Association for Computational Linguistics.