@inproceedings{liu-etal-2025-findabench,
title = "{F}in{DAB}ench: Benchmarking Financial Data Analysis Ability of Large Language Models",
author = "Liu, Shu and
Zhao, Shangqing and
Jia, Chenghao and
Zhuang, Xinlin and
Long, Zhaoguang and
Zhou, Jie and
Zhou, Aimin and
Lan, Man and
Chong, Yang",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.48/",
pages = "710--725",
abstract = "Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks. However, their proficiency and reliability in the specialized domain of financial data analysis, particularly focusing on data-driven thinking, remain uncertain. To bridge this gap, we introduce FinDABench, a comprehensive benchmark designed to evaluate the financial data analysis capabilities of LLMs within this context. The benchmark comprises 15,200 training instances and 8,900 test instances, all meticulously crafted by human experts. FinDABench assesses LLMs across three dimensions: 1) Core Ability, evaluating the models' ability to perform financial indicator calculation and corporate sentiment risk assessment; 2) Analytical Ability, determining the models' ability to quickly comprehend textual information and analyze abnormal financial reports; and 3) Technical Ability, examining the models' use of technical knowledge to address real-world data analysis challenges involving analysis generation and charts visualization from multiple perspectives. We will release FinDABench, and the evaluation scripts at https://github.com/xxx. FinDABench aims to provide a measure for in-depth analysis of LLM abilities and foster the advancement of LLMs in the field of financial data analysis."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-findabench">
<titleInfo>
<title>FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shangqing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghao</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinlin</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoguang</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aimin</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Man</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Chong</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 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</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>Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks. However, their proficiency and reliability in the specialized domain of financial data analysis, particularly focusing on data-driven thinking, remain uncertain. To bridge this gap, we introduce FinDABench, a comprehensive benchmark designed to evaluate the financial data analysis capabilities of LLMs within this context. The benchmark comprises 15,200 training instances and 8,900 test instances, all meticulously crafted by human experts. FinDABench assesses LLMs across three dimensions: 1) Core Ability, evaluating the models’ ability to perform financial indicator calculation and corporate sentiment risk assessment; 2) Analytical Ability, determining the models’ ability to quickly comprehend textual information and analyze abnormal financial reports; and 3) Technical Ability, examining the models’ use of technical knowledge to address real-world data analysis challenges involving analysis generation and charts visualization from multiple perspectives. We will release FinDABench, and the evaluation scripts at https://github.com/xxx. FinDABench aims to provide a measure for in-depth analysis of LLM abilities and foster the advancement of LLMs in the field of financial data analysis.</abstract>
<identifier type="citekey">liu-etal-2025-findabench</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.48/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>710</start>
<end>725</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models
%A Liu, Shu
%A Zhao, Shangqing
%A Jia, Chenghao
%A Zhuang, Xinlin
%A Long, Zhaoguang
%A Zhou, Jie
%A Zhou, Aimin
%A Lan, Man
%A Chong, Yang
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F liu-etal-2025-findabench
%X Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks. However, their proficiency and reliability in the specialized domain of financial data analysis, particularly focusing on data-driven thinking, remain uncertain. To bridge this gap, we introduce FinDABench, a comprehensive benchmark designed to evaluate the financial data analysis capabilities of LLMs within this context. The benchmark comprises 15,200 training instances and 8,900 test instances, all meticulously crafted by human experts. FinDABench assesses LLMs across three dimensions: 1) Core Ability, evaluating the models’ ability to perform financial indicator calculation and corporate sentiment risk assessment; 2) Analytical Ability, determining the models’ ability to quickly comprehend textual information and analyze abnormal financial reports; and 3) Technical Ability, examining the models’ use of technical knowledge to address real-world data analysis challenges involving analysis generation and charts visualization from multiple perspectives. We will release FinDABench, and the evaluation scripts at https://github.com/xxx. FinDABench aims to provide a measure for in-depth analysis of LLM abilities and foster the advancement of LLMs in the field of financial data analysis.
%U https://aclanthology.org/2025.coling-main.48/
%P 710-725
Markdown (Informal)
[FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models](https://aclanthology.org/2025.coling-main.48/) (Liu et al., COLING 2025)
ACL
- Shu Liu, Shangqing Zhao, Chenghao Jia, Xinlin Zhuang, Zhaoguang Long, Jie Zhou, Aimin Zhou, Man Lan, and Yang Chong. 2025. FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models. In Proceedings of the 31st International Conference on Computational Linguistics, pages 710–725, Abu Dhabi, UAE. Association for Computational Linguistics.