@inproceedings{hossein-zadeh-etal-2025-iust,
title = "{IUST}{\_}{C}hamps at {S}em{E}val-2025 Task 8: Structured Prompting and Retry Policy for Tabular Question Answering",
author = "Hossein Zadeh, Arshia and
Mayahinia, Aysa and
Ahmadi, Nafiseh",
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-1.260/",
pages = "2008--2013",
ISBN = "979-8-89176-273-2",
abstract = "This paper presents a novel approach to Question Answering over Tabular Data, as part of SemEval-2025 Task 8. Our system generates executable Python code to derive answers directly from structured data, leveraging open-source large language models. Key innovations include structured prompting, semantic column filtering, and a one-time retry mechanism to enhance accuracy and robustness. We evaluate our approach on the DataBench and DataBench{\_}Lite datasets, significantly outperforming the baseline accuracy (26-27{\%}) with our best system achieving 70.49{\%} accuracy on the test set. Ablation studies confirm that few-shot prompting and rule-based type classification are crucial for improved performance. Despite these advancements, challenges remain in handling complex table structures and ambiguous queries. Our findings highlight the effectiveness of code-generation based methods for tabular question answering and provide insights for further research in this area."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hossein-zadeh-etal-2025-iust">
<titleInfo>
<title>IUST_Champs at SemEval-2025 Task 8: Structured Prompting and Retry Policy for Tabular Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arshia</namePart>
<namePart type="family">Hossein Zadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aysa</namePart>
<namePart type="family">Mayahinia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nafiseh</namePart>
<namePart type="family">Ahmadi</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 presents a novel approach to Question Answering over Tabular Data, as part of SemEval-2025 Task 8. Our system generates executable Python code to derive answers directly from structured data, leveraging open-source large language models. Key innovations include structured prompting, semantic column filtering, and a one-time retry mechanism to enhance accuracy and robustness. We evaluate our approach on the DataBench and DataBench_Lite datasets, significantly outperforming the baseline accuracy (26-27%) with our best system achieving 70.49% accuracy on the test set. Ablation studies confirm that few-shot prompting and rule-based type classification are crucial for improved performance. Despite these advancements, challenges remain in handling complex table structures and ambiguous queries. Our findings highlight the effectiveness of code-generation based methods for tabular question answering and provide insights for further research in this area.</abstract>
<identifier type="citekey">hossein-zadeh-etal-2025-iust</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.260/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2008</start>
<end>2013</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IUST_Champs at SemEval-2025 Task 8: Structured Prompting and Retry Policy for Tabular Question Answering
%A Hossein Zadeh, Arshia
%A Mayahinia, Aysa
%A Ahmadi, Nafiseh
%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 hossein-zadeh-etal-2025-iust
%X This paper presents a novel approach to Question Answering over Tabular Data, as part of SemEval-2025 Task 8. Our system generates executable Python code to derive answers directly from structured data, leveraging open-source large language models. Key innovations include structured prompting, semantic column filtering, and a one-time retry mechanism to enhance accuracy and robustness. We evaluate our approach on the DataBench and DataBench_Lite datasets, significantly outperforming the baseline accuracy (26-27%) with our best system achieving 70.49% accuracy on the test set. Ablation studies confirm that few-shot prompting and rule-based type classification are crucial for improved performance. Despite these advancements, challenges remain in handling complex table structures and ambiguous queries. Our findings highlight the effectiveness of code-generation based methods for tabular question answering and provide insights for further research in this area.
%U https://aclanthology.org/2025.semeval-1.260/
%P 2008-2013
Markdown (Informal)
[IUST_Champs at SemEval-2025 Task 8: Structured Prompting and Retry Policy for Tabular Question Answering](https://aclanthology.org/2025.semeval-1.260/) (Hossein Zadeh et al., SemEval 2025)
ACL