@inproceedings{strich-2025-adapt,
title = "Adapt {LLM} for Multi-turn Reasoning {QA} using Tidy Data",
author = "Strich, Jan",
editor = "Chen, Chung-Chi and
Moreno-Sandoval, Antonio and
Huang, Jimin and
Xie, Qianqian and
Ananiadou, Sophia and
Chen, Hsin-Hsi",
booktitle = "Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.finnlp-1.45/",
pages = "392--400",
abstract = "This paper presents our submission to the Fin-DBQA shared task at the 9th FinNLP workshop. The task involves answering finance-focused questions in a multi-turn environment, requiring step-by-step reasoning and Python code generation. We propose a novel approach to tackle this multidimensional problem by pre-processing the data into tidy data format so that each column represents a variable and each row an observation. Our experiments demonstrate that using the tidy data format allows all models to surpass SOTA, with GPT-4o achieving a 50.62{\%} accuracy on the DBQR-QA benchmark achieving second place on the shared task leaderboard. These findings suggest that transforming data into the tidy data format enhances reasoning capabilities, reduces syntax errors, and improves performance on table-reasoning QA tasks. The code is available online."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strich-2025-adapt">
<titleInfo>
<title>Adapt LLM for Multi-turn Reasoning QA using Tidy Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Strich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Moreno-Sandoval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our submission to the Fin-DBQA shared task at the 9th FinNLP workshop. The task involves answering finance-focused questions in a multi-turn environment, requiring step-by-step reasoning and Python code generation. We propose a novel approach to tackle this multidimensional problem by pre-processing the data into tidy data format so that each column represents a variable and each row an observation. Our experiments demonstrate that using the tidy data format allows all models to surpass SOTA, with GPT-4o achieving a 50.62% accuracy on the DBQR-QA benchmark achieving second place on the shared task leaderboard. These findings suggest that transforming data into the tidy data format enhances reasoning capabilities, reduces syntax errors, and improves performance on table-reasoning QA tasks. The code is available online.</abstract>
<identifier type="citekey">strich-2025-adapt</identifier>
<location>
<url>https://aclanthology.org/2025.finnlp-1.45/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>392</start>
<end>400</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapt LLM for Multi-turn Reasoning QA using Tidy Data
%A Strich, Jan
%Y Chen, Chung-Chi
%Y Moreno-Sandoval, Antonio
%Y Huang, Jimin
%Y Xie, Qianqian
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%S Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F strich-2025-adapt
%X This paper presents our submission to the Fin-DBQA shared task at the 9th FinNLP workshop. The task involves answering finance-focused questions in a multi-turn environment, requiring step-by-step reasoning and Python code generation. We propose a novel approach to tackle this multidimensional problem by pre-processing the data into tidy data format so that each column represents a variable and each row an observation. Our experiments demonstrate that using the tidy data format allows all models to surpass SOTA, with GPT-4o achieving a 50.62% accuracy on the DBQR-QA benchmark achieving second place on the shared task leaderboard. These findings suggest that transforming data into the tidy data format enhances reasoning capabilities, reduces syntax errors, and improves performance on table-reasoning QA tasks. The code is available online.
%U https://aclanthology.org/2025.finnlp-1.45/
%P 392-400
Markdown (Informal)
[Adapt LLM for Multi-turn Reasoning QA using Tidy Data](https://aclanthology.org/2025.finnlp-1.45/) (Strich, FinNLP 2025)
ACL
- Jan Strich. 2025. Adapt LLM for Multi-turn Reasoning QA using Tidy Data. In Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal), pages 392–400, Abu Dhabi, UAE. Association for Computational Linguistics.