@inproceedings{rahnamoun-shamsfard-2025-sbu,
title = "{SBU}-{NLP} at {S}em{E}val-2025 Task 8: Self-Correction and Collaboration in {LLM}s for Tabular Question Answering",
author = "Rahnamoun, Rashin and
Shamsfard, Mehrnoush",
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.97/",
pages = "703--711",
ISBN = "979-8-89176-273-2",
abstract = "This paper explains the submission of the SBU-NLP team at SemEval-2025 Task 8: question-answering over tabular data. We present a novel algorithm for this task, aimed at systems capable of interpreting large tables and providing accurate answers to natural language queries. The evaluation uses the DataBench dataset, which covers a wide range of topics and reflects the complexity of real-world tabular data. Our approach incorporates a self-correction mechanism that iteratively refines LLM-generated code to address errors and prevent common mistakes. Additionally, a multi-LLM collaborative strategy is employed to generate answers, where responses from multiple LLMs are compared, and the majority consensus or a valid alternative is selected. The method relies exclusively on open-source models, avoiding costly processes like training or fine-tuning. Experimental results demonstrate that combining multiple LLMs with self-correction leads to significant performance improvements. However, challenges arise with list-based answers and responses involving multiple numerical, string, or boolean values, where further refinement is needed. The proposed simple system was among the top performers in both Subtask A and Subtask B among open-source models in the competition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahnamoun-shamsfard-2025-sbu">
<titleInfo>
<title>SBU-NLP at SemEval-2025 Task 8: Self-Correction and Collaboration in LLMs for Tabular Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rashin</namePart>
<namePart type="family">Rahnamoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehrnoush</namePart>
<namePart type="family">Shamsfard</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>This paper explains the submission of the SBU-NLP team at SemEval-2025 Task 8: question-answering over tabular data. We present a novel algorithm for this task, aimed at systems capable of interpreting large tables and providing accurate answers to natural language queries. The evaluation uses the DataBench dataset, which covers a wide range of topics and reflects the complexity of real-world tabular data. Our approach incorporates a self-correction mechanism that iteratively refines LLM-generated code to address errors and prevent common mistakes. Additionally, a multi-LLM collaborative strategy is employed to generate answers, where responses from multiple LLMs are compared, and the majority consensus or a valid alternative is selected. The method relies exclusively on open-source models, avoiding costly processes like training or fine-tuning. Experimental results demonstrate that combining multiple LLMs with self-correction leads to significant performance improvements. However, challenges arise with list-based answers and responses involving multiple numerical, string, or boolean values, where further refinement is needed. The proposed simple system was among the top performers in both Subtask A and Subtask B among open-source models in the competition.</abstract>
<identifier type="citekey">rahnamoun-shamsfard-2025-sbu</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.97/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>703</start>
<end>711</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SBU-NLP at SemEval-2025 Task 8: Self-Correction and Collaboration in LLMs for Tabular Question Answering
%A Rahnamoun, Rashin
%A Shamsfard, Mehrnoush
%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 rahnamoun-shamsfard-2025-sbu
%X This paper explains the submission of the SBU-NLP team at SemEval-2025 Task 8: question-answering over tabular data. We present a novel algorithm for this task, aimed at systems capable of interpreting large tables and providing accurate answers to natural language queries. The evaluation uses the DataBench dataset, which covers a wide range of topics and reflects the complexity of real-world tabular data. Our approach incorporates a self-correction mechanism that iteratively refines LLM-generated code to address errors and prevent common mistakes. Additionally, a multi-LLM collaborative strategy is employed to generate answers, where responses from multiple LLMs are compared, and the majority consensus or a valid alternative is selected. The method relies exclusively on open-source models, avoiding costly processes like training or fine-tuning. Experimental results demonstrate that combining multiple LLMs with self-correction leads to significant performance improvements. However, challenges arise with list-based answers and responses involving multiple numerical, string, or boolean values, where further refinement is needed. The proposed simple system was among the top performers in both Subtask A and Subtask B among open-source models in the competition.
%U https://aclanthology.org/2025.semeval-1.97/
%P 703-711
Markdown (Informal)
[SBU-NLP at SemEval-2025 Task 8: Self-Correction and Collaboration in LLMs for Tabular Question Answering](https://aclanthology.org/2025.semeval-1.97/) (Rahnamoun & Shamsfard, SemEval 2025)
ACL