<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galang-etal-2026-verify">
    <titleInfo>
        <title>Verify, Then Argue: Claim Verification in Investment Agent Debates</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Joyce</namePart>
        <namePart type="given">Ann</namePart>
        <namePart type="given">Clarize</namePart>
        <namePart type="family">Galang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ahmed</namePart>
        <namePart type="family">Mady</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Georg</namePart>
        <namePart type="family">Groh</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: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</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">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>Multi-agent debate systems incorporate retrieval-based verification to ground agent reasoning with evidence. However, this approach assumes the availability of data and the informative intent of the source text. These conditions are frequently unmet in venture capital, particularly in early-stage startup evaluation. In this industry, evidence is predominantly private or unavailable, and pitch decks use persuasive rhetoric that prior research shows can shift agent conclusions. To measure how agents navigate these conditions, we evaluate how claim verification alters multi-agent debate using a stratified sample of deals from a real venture fund. We find that verification changes the agent’s final investment decision but not its reasoning. Furthermore, agents are insensitive to which claim a verification label is attached to. Reassigning labels to the wrong claims lowers the decision to the same extent. This indicates that the primary bottleneck in automated screening is fundamental claim verifiability rather than retrieval quality.</abstract>
    <identifier type="citekey">galang-etal-2026-verify</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.243/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>4105</start>
            <end>4119</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Verify, Then Argue: Claim Verification in Investment Agent Debates
%A Galang, Joyce Ann Clarize
%A Mady, Ahmed
%A Groh, Georg
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F galang-etal-2026-verify
%X Multi-agent debate systems incorporate retrieval-based verification to ground agent reasoning with evidence. However, this approach assumes the availability of data and the informative intent of the source text. These conditions are frequently unmet in venture capital, particularly in early-stage startup evaluation. In this industry, evidence is predominantly private or unavailable, and pitch decks use persuasive rhetoric that prior research shows can shift agent conclusions. To measure how agents navigate these conditions, we evaluate how claim verification alters multi-agent debate using a stratified sample of deals from a real venture fund. We find that verification changes the agent’s final investment decision but not its reasoning. Furthermore, agents are insensitive to which claim a verification label is attached to. Reassigning labels to the wrong claims lowers the decision to the same extent. This indicates that the primary bottleneck in automated screening is fundamental claim verifiability rather than retrieval quality.
%U https://aclanthology.org/2026.emnlp-industry.243/
%P 4105-4119

Markdown (Informal)

[Verify, Then Argue: Claim Verification in Investment Agent Debates](https://aclanthology.org/2026.emnlp-industry.243/) (Galang et al., EMNLP 2026)

• Verify, Then Argue: Claim Verification in Investment Agent Debates (Galang et al., EMNLP 2026)

ACL

• Joyce Ann Clarize Galang, Ahmed Mady, and Georg Groh. 2026. Verify, Then Argue: Claim Verification in Investment Agent Debates. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 4105–4119, Budapest, Hungary. Association for Computational Linguistics.