<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanakarajan-etal-2025-saama">
    <titleInfo>
        <title>Saama Technologies at SemEval-2025 Task 8: Few-shot prompting with LLM-generated examples for question answering on tabular data</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kamal</namePart>
        <namePart type="given">Raj</namePart>
        <namePart type="family">Kanakarajan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hwanmun</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Malaikannan</namePart>
        <namePart type="family">Sankarasubbu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Rosenthal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aiala</namePart>
            <namePart type="family">Rosá</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcos</namePart>
            <namePart type="family">Zampieri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-273-2</identifier>
    </relatedItem>
    <abstract>For SemEval 2025 Task 8, addressing tabular data question answering, we introduce a novel few-shot prompting system that guides large language models (LLMs) to generate Python code representing the reasoning process. Our system automatically creates a library of exemplar code snippets from training data, which are then used for few-shot prompting. Crucially, we incorporate a selection prompt to choose the best candidate code from multiple LLM-generated options, improving robustness and accuracy. Our system achieved competitive results, ranking 17th in the Open Model track and 25th overall. Ablation studies demonstrate the effectiveness of our exemplar generation and code selection strategies. We conclude with a discussion of limitations and promising avenues for future research.</abstract>
    <identifier type="citekey">kanakarajan-etal-2025-saama</identifier>
    <location>
        <url>https://aclanthology.org/2025.semeval-1.165/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>1241</start>
            <end>1247</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Saama Technologies at SemEval-2025 Task 8: Few-shot prompting with LLM-generated examples for question answering on tabular data
%A Kanakarajan, Kamal Raj
%A Kim, Hwanmun
%A Sankarasubbu, Malaikannan
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F kanakarajan-etal-2025-saama
%X For SemEval 2025 Task 8, addressing tabular data question answering, we introduce a novel few-shot prompting system that guides large language models (LLMs) to generate Python code representing the reasoning process. Our system automatically creates a library of exemplar code snippets from training data, which are then used for few-shot prompting. Crucially, we incorporate a selection prompt to choose the best candidate code from multiple LLM-generated options, improving robustness and accuracy. Our system achieved competitive results, ranking 17th in the Open Model track and 25th overall. Ablation studies demonstrate the effectiveness of our exemplar generation and code selection strategies. We conclude with a discussion of limitations and promising avenues for future research.
%U https://aclanthology.org/2025.semeval-1.165/
%P 1241-1247

Markdown (Informal)

[Saama Technologies at SemEval-2025 Task 8: Few-shot prompting with LLM-generated examples for question answering on tabular data](https://aclanthology.org/2025.semeval-1.165/) (Kanakarajan et al., SemEval 2025)

• Saama Technologies at SemEval-2025 Task 8: Few-shot prompting with LLM-generated examples for question answering on tabular data (Kanakarajan et al., SemEval 2025)

ACL

• Kamal Raj Kanakarajan, Hwanmun Kim, and Malaikannan Sankarasubbu. 2025. Saama Technologies at SemEval-2025 Task 8: Few-shot prompting with LLM-generated examples for question answering on tabular data. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 1241–1247, Vienna, Austria. Association for Computational Linguistics.