<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lian-etal-2026-llm">
    <titleInfo>
        <title>How LLM Financial Agents Respond to Stated Affect Depends on Their Assigned Role</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Da</namePart>
        <namePart type="given">Chen</namePart>
        <namePart type="family">Lian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu-Lin</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yen-Hsi</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shu-Kai</namePart>
        <namePart type="family">Hsieh</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 11th Workshop on Financial Technology and Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jimin</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yongjae</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sophia</namePart>
            <namePart type="family">Ananiadou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hsin-Hsi</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hiroya</namePart>
            <namePart type="family">Takamura</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chung-Chi</namePart>
            <namePart type="family">Chen</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">979-8-89176-466-8</identifier>
    </relatedItem>
    <abstract>We test whether financial LLM agents respond differently to reports with identical facts, forecasts and recommendations but different wording. The reports differ only in a closing sentence stating the sender’s affect. The most consistent finding is linguistic: high-arousal wording increases readers’ word-based arousal scores on average and also changes teammates’ language. The response varies across rolespecific task instructions, although its magnitude and ordering change across prompt paraphrases, scoring methods, word-removal controls and model families. The central role comparison contains 7,080 generations, but all concern one underlying deposit-outflow event; the 59 matched pairs are seeded realizations of the same financial payload rather than independent financial situations. Separately varying alarm and urgency shows that both raise word-based arousal, while alarmed wording adds an apprehension component detected by an emotion classifier. Behavioral effects are less consistent: in the primary model, alarmed wording reduces adherence to BUY and SELL recommendations, but the SELL reported-size effect is not detected in two additional model families. A filter that removes explicit alarm while preserving checked financial fields leaves most of the linguistic response intact.</abstract>
    <identifier type="citekey">lian-etal-2026-llm</identifier>
    <location>
        <url>https://aclanthology.org/2026.finnlp-1.38/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>454</start>
            <end>468</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T How LLM Financial Agents Respond to Stated Affect Depends on Their Assigned Role
%A Lian, Da Chen
%A Chang, Yu-Lin
%A Huang, Yen-Hsi
%A Hsieh, Shu-Kai
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F lian-etal-2026-llm
%X We test whether financial LLM agents respond differently to reports with identical facts, forecasts and recommendations but different wording. The reports differ only in a closing sentence stating the sender’s affect. The most consistent finding is linguistic: high-arousal wording increases readers’ word-based arousal scores on average and also changes teammates’ language. The response varies across rolespecific task instructions, although its magnitude and ordering change across prompt paraphrases, scoring methods, word-removal controls and model families. The central role comparison contains 7,080 generations, but all concern one underlying deposit-outflow event; the 59 matched pairs are seeded realizations of the same financial payload rather than independent financial situations. Separately varying alarm and urgency shows that both raise word-based arousal, while alarmed wording adds an apprehension component detected by an emotion classifier. Behavioral effects are less consistent: in the primary model, alarmed wording reduces adherence to BUY and SELL recommendations, but the SELL reported-size effect is not detected in two additional model families. A filter that removes explicit alarm while preserving checked financial fields leaves most of the linguistic response intact.
%U https://aclanthology.org/2026.finnlp-1.38/
%P 454-468

Markdown (Informal)

[How LLM Financial Agents Respond to Stated Affect Depends on Their Assigned Role](https://aclanthology.org/2026.finnlp-1.38/) (Lian et al., FinNLP 2026)

• How LLM Financial Agents Respond to Stated Affect Depends on Their Assigned Role (Lian et al., FinNLP 2026)

ACL

• Da Chen Lian, Yu-Lin Chang, Yen-Hsi Huang, and Shu-Kai Hsieh. 2026. How LLM Financial Agents Respond to Stated Affect Depends on Their Assigned Role. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 454–468, Budapest, Hungary. Association for Computational Linguistics.