<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gebele-etal-2026-diversity">
    <titleInfo>
        <title>Diversity and Deliberation in Homogeneous LLM Prediction Polls</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jonas</namePart>
        <namePart type="family">Gebele</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tristan</namePart>
        <namePart type="family">Till</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Florian</namePart>
        <namePart type="family">Matthes</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolai</namePart>
            <namePart type="family">Rozanov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maryam</namePart>
            <namePart type="family">Hashemzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akhil</namePart>
            <namePart type="family">Arora</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">979-8-89176-485-9</identifier>
    </relatedItem>
    <abstract>Multi-agent large language model (LLM) systems increasingly combine model-generated judgments for forecasting and collective decision-making. However, homogeneous agent systems, i.e., those that share a model and evidence, may produce correlated forecasts, and communication may further contract the diversity that remains. We examine these issues in live LLM prediction polls. Across 189 resolved snapshots, mean residual-error correlation was 0.910. Semantic prompt differences were associated with forecast differences, but diversity-aware selection did not detectably outperform prespecified random ensembles. Standard deliberation removed approximately twice as much disagreement benefit as it added through improvements in individual forecasts at the point estimates, with no detectable improvement in aggregate accuracy. In a prospective intervention, a probability-blind summary of forecast-relevant claims retained 93% of initial dispersion, compared with 29% under standard exchange.</abstract>
    <identifier type="citekey">gebele-etal-2026-diversity</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.85/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1229</start>
            <end>1235</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Diversity and Deliberation in Homogeneous LLM Prediction Polls
%A Gebele, Jonas
%A Till, Tristan
%A Matthes, Florian
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F gebele-etal-2026-diversity
%X Multi-agent large language model (LLM) systems increasingly combine model-generated judgments for forecasting and collective decision-making. However, homogeneous agent systems, i.e., those that share a model and evidence, may produce correlated forecasts, and communication may further contract the diversity that remains. We examine these issues in live LLM prediction polls. Across 189 resolved snapshots, mean residual-error correlation was 0.910. Semantic prompt differences were associated with forecast differences, but diversity-aware selection did not detectably outperform prespecified random ensembles. Standard deliberation removed approximately twice as much disagreement benefit as it added through improvements in individual forecasts at the point estimates, with no detectable improvement in aggregate accuracy. In a prospective intervention, a probability-blind summary of forecast-relevant claims retained 93% of initial dispersion, compared with 29% under standard exchange.
%U https://aclanthology.org/2026.realm-1.85/
%P 1229-1235

Markdown (Informal)

[Diversity and Deliberation in Homogeneous LLM Prediction Polls](https://aclanthology.org/2026.realm-1.85/) (Gebele et al., REALM 2026)

• Diversity and Deliberation in Homogeneous LLM Prediction Polls (Gebele et al., REALM 2026)

ACL

• Jonas Gebele, Tristan Till, and Florian Matthes. 2026. Diversity and Deliberation in Homogeneous LLM Prediction Polls. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 1229–1235, Budapest, Hungary. Association for Computational Linguistics.