@inproceedings{site-etal-2025-itunlp,
title = "{ITUNLP} at {S}em{E}val-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using {LLM}-Driven Code Generation",
author = {Site, Atakan and
Erdemir, Emre and
Eryi{\u{g}}it, G{\"u}l{\c{s}}en},
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-1.198/",
pages = "1504--1514",
ISBN = "979-8-89176-273-2",
abstract = "This paper presents our system for SemEval-2025 Task 8: DataBench, Question-Answeringover Tabular Data. The primary objective ofthis task is to perform question answering ongiven tabular datasets from diverse domains;under two subtasks: DataBench QA (SubtaskI) and DataBench Lite QA (Subtask II). Totackle both subtasks, we developed a zero-shotsolution with a particular emphasis on lever-aging Large Language Model (LLM)-basedcode generation. Specifically, we proposeda Python code generation framework, utiliz-ing state-of-the-art open-source LLMs to gen-erate executable Pandas code via optimizedprompting strategies. Our experiments revealthat different LLMs exhibit varying levels ofeffectiveness in Python code generation. Addi-tionaly, results show that Python code genera-tion achieves superior performance in tabularquestion answering compared to alternative ap-proaches. Although our ranking among zero-shot systems is unknown at the time of this pa-per{'}s submission, our system achieved eighthplace in Subtask I and sixth place in Subtask IIamong the 30 systems that outperformed thebaseline in the open-source models category."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="site-etal-2025-itunlp">
<titleInfo>
<title>ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atakan</namePart>
<namePart type="family">Site</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emre</namePart>
<namePart type="family">Erdemir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gülşen</namePart>
<namePart type="family">Eryiğit</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 our system for SemEval-2025 Task 8: DataBench, Question-Answeringover Tabular Data. The primary objective ofthis task is to perform question answering ongiven tabular datasets from diverse domains;under two subtasks: DataBench QA (SubtaskI) and DataBench Lite QA (Subtask II). Totackle both subtasks, we developed a zero-shotsolution with a particular emphasis on lever-aging Large Language Model (LLM)-basedcode generation. Specifically, we proposeda Python code generation framework, utiliz-ing state-of-the-art open-source LLMs to gen-erate executable Pandas code via optimizedprompting strategies. Our experiments revealthat different LLMs exhibit varying levels ofeffectiveness in Python code generation. Addi-tionaly, results show that Python code genera-tion achieves superior performance in tabularquestion answering compared to alternative ap-proaches. Although our ranking among zero-shot systems is unknown at the time of this pa-per’s submission, our system achieved eighthplace in Subtask I and sixth place in Subtask IIamong the 30 systems that outperformed thebaseline in the open-source models category.</abstract>
<identifier type="citekey">site-etal-2025-itunlp</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.198/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1504</start>
<end>1514</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generation
%A Site, Atakan
%A Erdemir, Emre
%A Eryiğit, Gülşen
%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 site-etal-2025-itunlp
%X This paper presents our system for SemEval-2025 Task 8: DataBench, Question-Answeringover Tabular Data. The primary objective ofthis task is to perform question answering ongiven tabular datasets from diverse domains;under two subtasks: DataBench QA (SubtaskI) and DataBench Lite QA (Subtask II). Totackle both subtasks, we developed a zero-shotsolution with a particular emphasis on lever-aging Large Language Model (LLM)-basedcode generation. Specifically, we proposeda Python code generation framework, utiliz-ing state-of-the-art open-source LLMs to gen-erate executable Pandas code via optimizedprompting strategies. Our experiments revealthat different LLMs exhibit varying levels ofeffectiveness in Python code generation. Addi-tionaly, results show that Python code genera-tion achieves superior performance in tabularquestion answering compared to alternative ap-proaches. Although our ranking among zero-shot systems is unknown at the time of this pa-per’s submission, our system achieved eighthplace in Subtask I and sixth place in Subtask IIamong the 30 systems that outperformed thebaseline in the open-source models category.
%U https://aclanthology.org/2025.semeval-1.198/
%P 1504-1514
Markdown (Informal)
[ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generation](https://aclanthology.org/2025.semeval-1.198/) (Site et al., SemEval 2025)
ACL