Sheffield NLP at FinCausal 2026: A Comparative Study of RAG Approaches and Fine-Tuning for Causal Q&A in Financial Texts

Aali Abdullah Alqarni; Mark Stevenson; Arif Dwi Laksito

doi:10.63317/3w3pbwvmc2mm

Sheffield NLP at FinCausal 2026: A Comparative Study of RAG Approaches and Fine-Tuning for Causal Q&A in Financial Texts

Aali Abdullah Alqarni, Mark Stevenson, Arif Dwi Laksito

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 external publication .)

Authors concatenated from the text boxes above:

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

Abstract

This paper describes our approach to the FinCausal 2026 shared task, which addresses causal question answering from financial documents in English and Spanish. We investigated the effectiveness of fine-tuned generative models combined with Retrieval-Augmented Generation (RAG). Our approach compares five retrieval strategies across base and fine-tuned GPT-models (GPT-4.1-mini). RAG-based few-shot selection showed better performance than random sampling, particularly for the base model. In the FinCausal 2026 official run, this approach was ranked first in both the English and Spanish subtasks, obtaining LLM scores of 4.8140 and 4.8131 out of 5, respectively.

Anthology ID:: 2026.fnp-1.12
Volume:: The 7th Financial Narrative Processing Workshop
Month:: May
Year:: 2026
Address:: Palma de Mallorca, Spain
Editors:: Mo El-Haj, Antonio Moreno Sandoval, Ana Garcia-Serrano, Chung-Chi Chen, Paul Rayson, Yanco Amor Torterolo Orta, Paloma Martinez, Jordi Porta
Venues:: FNP | WS
SIG:
Publisher:: European Language Resources Association (ELRA)
Note:
Pages:: 125–131
Language:
External URL:: https://lrec.elra.info/lrec2026-ws-fnp-12
DOI:: 10.63317/3w3pbwvmc2mm
Bibkey:
Cite (ACL):: Aali Abdullah Alqarni, Mark Stevenson, and Arif Dwi Laksito. 2026. Sheffield NLP at FinCausal 2026: A Comparative Study of RAG Approaches and Fine-Tuning for Causal Q&A in Financial Texts. In The 7th Financial Narrative Processing Workshop, pages 125–131, Palma de Mallorca, Spain. European Language Resources Association (ELRA).
Cite (Informal):: Sheffield NLP at FinCausal 2026: A Comparative Study of RAG Approaches and Fine-Tuning for Causal Q&A in Financial Texts (Alqarni et al., FNP 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{alqarni-etal-2026-sheffield,
    title = "{S}heffield {NLP} at {F}in{C}ausal 2026: A Comparative Study of {RAG} Approaches and Fine-Tuning for Causal {Q}{\&}{A} in Financial Texts",
    author = "Alqarni, Aali Abdullah  and
      Stevenson, Mark  and
      Laksito, Arif Dwi",
    editor = "El-Haj, Mo  and
      Moreno Sandoval, Antonio  and
      Garcia-Serrano, Ana  and
      Chen, Chung-Chi  and
      Rayson, Paul  and
      Torterolo Orta, Yanco Amor  and
      Martinez, Paloma  and
      Porta, Jordi",
    booktitle = "The 7th Financial Narrative Processing Workshop",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.fnp-1.12/",
    doi = "10.63317/3w3pbwvmc2mm",
    pages = "125--131",
    abstract = "This paper describes our approach to the FinCausal 2026 shared task, which addresses causal question answering from financial documents in English and Spanish. We investigated the effectiveness of fine-tuned generative models combined with Retrieval-Augmented Generation (RAG). Our approach compares five retrieval strategies across base and fine-tuned GPT-models (GPT-4.1-mini). RAG-based few-shot selection showed better performance than random sampling, particularly for the base model. In the FinCausal 2026 official run, this approach was ranked first in both the English and Spanish subtasks, obtaining LLM scores of 4.8140 and 4.8131 out of 5, respectively."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alqarni-etal-2026-sheffield">
    <titleInfo>
        <title>Sheffield NLP at FinCausal 2026: A Comparative Study of RAG Approaches and Fine-Tuning for Causal Q&amp;A in Financial Texts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Aali</namePart>
        <namePart type="given">Abdullah</namePart>
        <namePart type="family">Alqarni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mark</namePart>
        <namePart type="family">Stevenson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arif</namePart>
        <namePart type="given">Dwi</namePart>
        <namePart type="family">Laksito</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>The 7th Financial Narrative Processing Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mo</namePart>
            <namePart type="family">El-Haj</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Moreno Sandoval</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ana</namePart>
            <namePart type="family">Garcia-Serrano</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>
        <name type="personal">
            <namePart type="given">Paul</namePart>
            <namePart type="family">Rayson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yanco</namePart>
            <namePart type="given">Amor</namePart>
            <namePart type="family">Torterolo Orta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Paloma</namePart>
            <namePart type="family">Martinez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordi</namePart>
            <namePart type="family">Porta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>European Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper describes our approach to the FinCausal 2026 shared task, which addresses causal question answering from financial documents in English and Spanish. We investigated the effectiveness of fine-tuned generative models combined with Retrieval-Augmented Generation (RAG). Our approach compares five retrieval strategies across base and fine-tuned GPT-models (GPT-4.1-mini). RAG-based few-shot selection showed better performance than random sampling, particularly for the base model. In the FinCausal 2026 official run, this approach was ranked first in both the English and Spanish subtasks, obtaining LLM scores of 4.8140 and 4.8131 out of 5, respectively.</abstract>
    <identifier type="citekey">alqarni-etal-2026-sheffield</identifier>
    <identifier type="doi">10.63317/3w3pbwvmc2mm</identifier>
    <location>
        <url>https://aclanthology.org/2026.fnp-1.12/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>125</start>
            <end>131</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Sheffield NLP at FinCausal 2026: A Comparative Study of RAG Approaches and Fine-Tuning for Causal Q&A in Financial Texts
%A Alqarni, Aali Abdullah
%A Stevenson, Mark
%A Laksito, Arif Dwi
%Y El-Haj, Mo
%Y Moreno Sandoval, Antonio
%Y Garcia-Serrano, Ana
%Y Chen, Chung-Chi
%Y Rayson, Paul
%Y Torterolo Orta, Yanco Amor
%Y Martinez, Paloma
%Y Porta, Jordi
%S The 7th Financial Narrative Processing Workshop
%D 2026
%8 May
%I European Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F alqarni-etal-2026-sheffield
%X This paper describes our approach to the FinCausal 2026 shared task, which addresses causal question answering from financial documents in English and Spanish. We investigated the effectiveness of fine-tuned generative models combined with Retrieval-Augmented Generation (RAG). Our approach compares five retrieval strategies across base and fine-tuned GPT-models (GPT-4.1-mini). RAG-based few-shot selection showed better performance than random sampling, particularly for the base model. In the FinCausal 2026 official run, this approach was ranked first in both the English and Spanish subtasks, obtaining LLM scores of 4.8140 and 4.8131 out of 5, respectively.
%R 10.63317/3w3pbwvmc2mm
%U https://aclanthology.org/2026.fnp-1.12/
%U https://doi.org/10.63317/3w3pbwvmc2mm
%P 125-131

Download as File

Markdown (Informal)

[Sheffield NLP at FinCausal 2026: A Comparative Study of RAG Approaches and Fine-Tuning for Causal Q&A in Financial Texts](https://aclanthology.org/2026.fnp-1.12/) (Alqarni et al., FNP 2026)

Sheffield NLP at FinCausal 2026: A Comparative Study of RAG Approaches and Fine-Tuning for Causal Q&A in Financial Texts (Alqarni et al., FNP 2026)

ACL

Aali Abdullah Alqarni, Mark Stevenson, and Arif Dwi Laksito. 2026. Sheffield NLP at FinCausal 2026: A Comparative Study of RAG Approaches and Fine-Tuning for Causal Q&A in Financial Texts. In The 7th Financial Narrative Processing Workshop, pages 125–131, Palma de Mallorca, Spain. European Language Resources Association (ELRA).