@inproceedings{zhao-etal-2024-knowledgefmath,
title = "{K}nowledge{FM}ath: A Knowledge-Intensive Math Reasoning Dataset in Finance Domains",
author = "Zhao, Yilun and
Liu, Hongjun and
Long, Yitao and
Zhang, Rui and
Zhao, Chen and
Cohan, Arman",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.693",
pages = "12841--12858",
abstract = "We introduce KnowledgeFMath, a novel benchmark designed to evaluate LLMs{'} capabilities in solving knowledge-intensive math reasoning problems. Compared to prior works, this study features three core advancements. First, KnowledgeFMath includes 1,259 problems with a hybrid of textual and tabular content. These problems require college-level knowledge in the finance domain for effective resolution. Second, we provide expert-annotated, detailed solution references in Python program format, ensuring a high-quality benchmark for LLM assessment. We also construct a finance-domain knowledge bank and investigate various knowledge integration strategies. Finally, we evaluate a wide spectrum of 26 LLMs with different prompting strategies like Chain-of-Thought and Program-of-Thought. Our experimental results reveal that the current best-performing system (i.e., GPT-4 with CoT prompting) achieves only 56.6{\%} accuracy, leaving substantial room for improvement. Moreover, while augmenting LLMs with external knowledge can improve their performance (e.g., from 33.5{\%} to 47.1{\%} for GPT-3.5), their accuracy remains significantly lower than the estimated human expert performance of 92{\%}. We believe that KnowledgeFMath can advance future research in the area of domain-specific knowledge retrieval and integration, particularly within the context of solving math reasoning problems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2024-knowledgefmath">
<titleInfo>
<title>KnowledgeFMath: A Knowledge-Intensive Math Reasoning Dataset in Finance Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yilun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongjun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yitao</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="family">Cohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce KnowledgeFMath, a novel benchmark designed to evaluate LLMs’ capabilities in solving knowledge-intensive math reasoning problems. Compared to prior works, this study features three core advancements. First, KnowledgeFMath includes 1,259 problems with a hybrid of textual and tabular content. These problems require college-level knowledge in the finance domain for effective resolution. Second, we provide expert-annotated, detailed solution references in Python program format, ensuring a high-quality benchmark for LLM assessment. We also construct a finance-domain knowledge bank and investigate various knowledge integration strategies. Finally, we evaluate a wide spectrum of 26 LLMs with different prompting strategies like Chain-of-Thought and Program-of-Thought. Our experimental results reveal that the current best-performing system (i.e., GPT-4 with CoT prompting) achieves only 56.6% accuracy, leaving substantial room for improvement. Moreover, while augmenting LLMs with external knowledge can improve their performance (e.g., from 33.5% to 47.1% for GPT-3.5), their accuracy remains significantly lower than the estimated human expert performance of 92%. We believe that KnowledgeFMath can advance future research in the area of domain-specific knowledge retrieval and integration, particularly within the context of solving math reasoning problems.</abstract>
<identifier type="citekey">zhao-etal-2024-knowledgefmath</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.693</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12841</start>
<end>12858</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KnowledgeFMath: A Knowledge-Intensive Math Reasoning Dataset in Finance Domains
%A Zhao, Yilun
%A Liu, Hongjun
%A Long, Yitao
%A Zhang, Rui
%A Zhao, Chen
%A Cohan, Arman
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhao-etal-2024-knowledgefmath
%X We introduce KnowledgeFMath, a novel benchmark designed to evaluate LLMs’ capabilities in solving knowledge-intensive math reasoning problems. Compared to prior works, this study features three core advancements. First, KnowledgeFMath includes 1,259 problems with a hybrid of textual and tabular content. These problems require college-level knowledge in the finance domain for effective resolution. Second, we provide expert-annotated, detailed solution references in Python program format, ensuring a high-quality benchmark for LLM assessment. We also construct a finance-domain knowledge bank and investigate various knowledge integration strategies. Finally, we evaluate a wide spectrum of 26 LLMs with different prompting strategies like Chain-of-Thought and Program-of-Thought. Our experimental results reveal that the current best-performing system (i.e., GPT-4 with CoT prompting) achieves only 56.6% accuracy, leaving substantial room for improvement. Moreover, while augmenting LLMs with external knowledge can improve their performance (e.g., from 33.5% to 47.1% for GPT-3.5), their accuracy remains significantly lower than the estimated human expert performance of 92%. We believe that KnowledgeFMath can advance future research in the area of domain-specific knowledge retrieval and integration, particularly within the context of solving math reasoning problems.
%U https://aclanthology.org/2024.acl-long.693
%P 12841-12858
Markdown (Informal)
[KnowledgeFMath: A Knowledge-Intensive Math Reasoning Dataset in Finance Domains](https://aclanthology.org/2024.acl-long.693) (Zhao et al., ACL 2024)
ACL