@inproceedings{turek-etal-2025-csiro,
title = "{CSIRO} {LT} at {S}em{E}val-2025 Task 8: Answering Questions over Tabular Data using {LLM}s",
author = "Turek, Tomas and
Tonni, Shakila Mahjabin and
Nguyen, Vincent and
Yang, Huichen and
Karimi, Sarvnaz",
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-1.222/",
pages = "1690--1701",
ISBN = "979-8-89176-273-2",
abstract = "Question Answering over large tables is challenging due to the difficulty of reasoning required in linking information from different parts of a table, such as heading and metadata to the values in the table and information needs. We investigate using Large Language Models (LLM) for tabular reasoning, where, given a pair of a table and a question from the DataBench benchmark, the models generate answers. We experiment with three techniques that enables symbolic reasoning through code execution: a direct code prompting (DCP) approach, `DCP{\_}Py', which uses Python, multi-step code (MSC) prompting `MSC{\_}SQL+FS' using SQL and ReAct prompting, `MSR{\_}Py+FS', which combines multi-step reasoning (MSR), few-shot (FS) learning and Python tools. We also conduct an analysis exploring the impact of answer types, data size, and multi-column dependencies on LLMs' answer generation performance, including an assessment of the models' limitations and the underlying challenges of tabular reasoning in LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="turek-etal-2025-csiro">
<titleInfo>
<title>CSIRO LT at SemEval-2025 Task 8: Answering Questions over Tabular Data using LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomas</namePart>
<namePart type="family">Turek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shakila</namePart>
<namePart type="given">Mahjabin</namePart>
<namePart type="family">Tonni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huichen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarvnaz</namePart>
<namePart type="family">Karimi</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>Question Answering over large tables is challenging due to the difficulty of reasoning required in linking information from different parts of a table, such as heading and metadata to the values in the table and information needs. We investigate using Large Language Models (LLM) for tabular reasoning, where, given a pair of a table and a question from the DataBench benchmark, the models generate answers. We experiment with three techniques that enables symbolic reasoning through code execution: a direct code prompting (DCP) approach, ‘DCP_Py’, which uses Python, multi-step code (MSC) prompting ‘MSC_SQL+FS’ using SQL and ReAct prompting, ‘MSR_Py+FS’, which combines multi-step reasoning (MSR), few-shot (FS) learning and Python tools. We also conduct an analysis exploring the impact of answer types, data size, and multi-column dependencies on LLMs’ answer generation performance, including an assessment of the models’ limitations and the underlying challenges of tabular reasoning in LLMs.</abstract>
<identifier type="citekey">turek-etal-2025-csiro</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.222/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1690</start>
<end>1701</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CSIRO LT at SemEval-2025 Task 8: Answering Questions over Tabular Data using LLMs
%A Turek, Tomas
%A Tonni, Shakila Mahjabin
%A Nguyen, Vincent
%A Yang, Huichen
%A Karimi, Sarvnaz
%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 turek-etal-2025-csiro
%X Question Answering over large tables is challenging due to the difficulty of reasoning required in linking information from different parts of a table, such as heading and metadata to the values in the table and information needs. We investigate using Large Language Models (LLM) for tabular reasoning, where, given a pair of a table and a question from the DataBench benchmark, the models generate answers. We experiment with three techniques that enables symbolic reasoning through code execution: a direct code prompting (DCP) approach, ‘DCP_Py’, which uses Python, multi-step code (MSC) prompting ‘MSC_SQL+FS’ using SQL and ReAct prompting, ‘MSR_Py+FS’, which combines multi-step reasoning (MSR), few-shot (FS) learning and Python tools. We also conduct an analysis exploring the impact of answer types, data size, and multi-column dependencies on LLMs’ answer generation performance, including an assessment of the models’ limitations and the underlying challenges of tabular reasoning in LLMs.
%U https://aclanthology.org/2025.semeval-1.222/
%P 1690-1701
Markdown (Informal)
[CSIRO LT at SemEval-2025 Task 8: Answering Questions over Tabular Data using LLMs](https://aclanthology.org/2025.semeval-1.222/) (Turek et al., SemEval 2025)
ACL