Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference

Yike Li; Adam Poliak

Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference

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

We present FinNLI-Para, a paraphrased version of financial natural language inference (FinNLI). We investigate how much predictions on FinNLI depend on the particular wording used to express a financial hypothesis. We generate three paraphrases for each FinNLI hypothesis and use them to test prediction consistency across eleven model–prompt configurations. Models change their predictions on 7.9–12.3% of paraphrased examples, despite 98.35% of paraphrases preserving the original NLI label, indicating that financial NLI systems remain sensitive to hypothesis wording.

Anthology ID:: 2026.finnlp-1.35
Volume:: Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Jimin Huang, Yongjae Lee, Sophia Ananiadou, Hsin-Hsi Chen, Hiroya Takamura, Chung-Chi Chen
Venues:: FinNLP | WS
SIG:: SIGFinTech
Publisher:: Association for Computational Linguistics
Note:
Pages:: 424–433
Language:
URL:: https://aclanthology.org/2026.finnlp-1.35/
DOI:
Bibkey:
Cite (ACL):: Yike Li and Adam Poliak. 2026. Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 424–433, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference (Li & Poliak, FinNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.finnlp-1.35.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{li-poliak-2026-meaning,
    title = "Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference",
    author = "Li, Yike  and
      Poliak, Adam",
    editor = "Huang, Jimin  and
      Lee, Yongjae  and
      Ananiadou, Sophia  and
      Chen, Hsin-Hsi  and
      Takamura, Hiroya  and
      Chen, Chung-Chi",
    booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.finnlp-1.35/",
    pages = "424--433",
    ISBN = "979-8-89176-466-8",
    abstract = "We present FinNLI-Para, a paraphrased version of financial natural language inference (FinNLI). We investigate how much predictions on FinNLI depend on the particular wording used to express a financial hypothesis. We generate three paraphrases for each FinNLI hypothesis and use them to test prediction consistency across eleven model{--}prompt configurations. Models change their predictions on 7.9{--}12.3{\%} of paraphrased examples, despite 98.35{\%} of paraphrases preserving the original NLI label, indicating that financial NLI systems remain sensitive to hypothesis wording."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-poliak-2026-meaning">
    <titleInfo>
        <title>Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yike</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Poliak</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 present FinNLI-Para, a paraphrased version of financial natural language inference (FinNLI). We investigate how much predictions on FinNLI depend on the particular wording used to express a financial hypothesis. We generate three paraphrases for each FinNLI hypothesis and use them to test prediction consistency across eleven model–prompt configurations. Models change their predictions on 7.9–12.3% of paraphrased examples, despite 98.35% of paraphrases preserving the original NLI label, indicating that financial NLI systems remain sensitive to hypothesis wording.</abstract>
    <identifier type="citekey">li-poliak-2026-meaning</identifier>
    <location>
        <url>https://aclanthology.org/2026.finnlp-1.35/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>424</start>
            <end>433</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference
%A Li, Yike
%A Poliak, Adam
%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 li-poliak-2026-meaning
%X We present FinNLI-Para, a paraphrased version of financial natural language inference (FinNLI). We investigate how much predictions on FinNLI depend on the particular wording used to express a financial hypothesis. We generate three paraphrases for each FinNLI hypothesis and use them to test prediction consistency across eleven model–prompt configurations. Models change their predictions on 7.9–12.3% of paraphrased examples, despite 98.35% of paraphrases preserving the original NLI label, indicating that financial NLI systems remain sensitive to hypothesis wording.
%U https://aclanthology.org/2026.finnlp-1.35/
%P 424-433

Download as File

Markdown (Informal)

[Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference](https://aclanthology.org/2026.finnlp-1.35/) (Li & Poliak, FinNLP 2026)

Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference (Li & Poliak, FinNLP 2026)

ACL

Yike Li and Adam Poliak. 2026. Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 424–433, Budapest, Hungary. Association for Computational Linguistics.