FinRAQ: Financial News Reasoning through Importance Ranking and Socratic Questioning

Zee Hen Tang; Mi-Yen Yeh

FinRAQ: Financial News Reasoning through Importance Ranking and Socratic Questioning

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

In financial markets, effective trading decisions require accurately interpreting unstructured information, especially news articles. However, prior work overlooks the complex news and agent interactions when making trading decisions. To address these limitations, we propose FinRAQ, which enhances the news importance scoring by modeling semantic and temporal interactions between news articles. FinRAQ incorporates a Socratic questioning stage into the debate framework, prompting agents to challenge each other’s reasoning through Socratic questions. Extensive experiments across six company stocks show that FinRAQ outperforms state-of-the-art baselines, achieving up to 38% improvement in annualized returns.

Anthology ID:: 2026.findings-emnlp.1432
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 30500–30547
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.1432/
DOI:
Bibkey:
Cite (ACL):: Zee Hen Tang and Mi-Yen Yeh. 2026. FinRAQ: Financial News Reasoning through Importance Ranking and Socratic Questioning. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 30500–30547, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: FinRAQ: Financial News Reasoning through Importance Ranking and Socratic Questioning (Tang & Yeh, Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.1432.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{tang-yeh-2026-finraq,
    title = "{F}in{RAQ}: Financial News Reasoning through Importance Ranking and Socratic Questioning",
    author = "Tang, Zee Hen  and
      Yeh, Mi-Yen",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1432/",
    pages = "30500--30547",
    ISBN = "979-8-89176-462-0",
    abstract = "In financial markets, effective trading decisions require accurately interpreting unstructured information, especially news articles. However, prior work overlooks the complex news and agent interactions when making trading decisions. To address these limitations, we propose FinRAQ, which enhances the news importance scoring by modeling semantic and temporal interactions between news articles. FinRAQ incorporates a Socratic questioning stage into the debate framework, prompting agents to challenge each other{'}s reasoning through Socratic questions. Extensive experiments across six company stocks show that FinRAQ outperforms state-of-the-art baselines, achieving up to 38{\%} improvement in annualized returns."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-yeh-2026-finraq">
    <titleInfo>
        <title>FinRAQ: Financial News Reasoning through Importance Ranking and Socratic Questioning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zee</namePart>
        <namePart type="given">Hen</namePart>
        <namePart type="family">Tang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mi-Yen</namePart>
        <namePart type="family">Yeh</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>In financial markets, effective trading decisions require accurately interpreting unstructured information, especially news articles. However, prior work overlooks the complex news and agent interactions when making trading decisions. To address these limitations, we propose FinRAQ, which enhances the news importance scoring by modeling semantic and temporal interactions between news articles. FinRAQ incorporates a Socratic questioning stage into the debate framework, prompting agents to challenge each other’s reasoning through Socratic questions. Extensive experiments across six company stocks show that FinRAQ outperforms state-of-the-art baselines, achieving up to 38% improvement in annualized returns.</abstract>
    <identifier type="citekey">tang-yeh-2026-finraq</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1432/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>30500</start>
            <end>30547</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T FinRAQ: Financial News Reasoning through Importance Ranking and Socratic Questioning
%A Tang, Zee Hen
%A Yeh, Mi-Yen
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F tang-yeh-2026-finraq
%X In financial markets, effective trading decisions require accurately interpreting unstructured information, especially news articles. However, prior work overlooks the complex news and agent interactions when making trading decisions. To address these limitations, we propose FinRAQ, which enhances the news importance scoring by modeling semantic and temporal interactions between news articles. FinRAQ incorporates a Socratic questioning stage into the debate framework, prompting agents to challenge each other’s reasoning through Socratic questions. Extensive experiments across six company stocks show that FinRAQ outperforms state-of-the-art baselines, achieving up to 38% improvement in annualized returns.
%U https://aclanthology.org/2026.findings-emnlp.1432/
%P 30500-30547

Download as File

Markdown (Informal)

[FinRAQ: Financial News Reasoning through Importance Ranking and Socratic Questioning](https://aclanthology.org/2026.findings-emnlp.1432/) (Tang & Yeh, Findings 2026)

FinRAQ: Financial News Reasoning through Importance Ranking and Socratic Questioning (Tang & Yeh, Findings 2026)

ACL

Zee Hen Tang and Mi-Yen Yeh. 2026. FinRAQ: Financial News Reasoning through Importance Ranking and Socratic Questioning. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 30500–30547, Budapest, Hungary. Association for Computational Linguistics.