@inproceedings{mahfouz-etal-2024-state,
title = "The State of the Art of Large Language Models on Chartered Financial Analyst Exams",
author = "Mahfouz, Mahmoud and
Callanan, Ethan and
Sibue, Mathieu and
Papadimitriou, Antony and
Ma, Zhiqiang and
Liu, Xiaomo and
Zhu, Xiaodan",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.80",
pages = "1068--1082",
abstract = "The Chartered Financial Analyst (CFA) program is one of the most widely recognized financial certifications globally. In this work, we test a variety of state-of-the-art large language models (LLMs) on mock CFA exams to provide an overview of their financial analysis capabilities using the same evaluation standards applied for human professionals. We benchmark five leading proprietary models and eight open-source models on all three levels of the CFA through challenging multiple-choice and essay questions. We find that flagship proprietary models perform relatively well and can solidly pass levels I and II exams, but fail at level III due to essay questions. Open-source models generally fall short of estimated passing scores, but still show strong performance considering their size, cost, and availability advantages. We also find that using textbook data helps bridge the gap between open-source and proprietary models to a certain extent, despite reduced gains in CFA levels II and III. By understanding the current financial analysis abilities of LLMs, we aim to guide practitioners on which models are best suited for enhancing automation in the financial industry.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahfouz-etal-2024-state">
<titleInfo>
<title>The State of the Art of Large Language Models on Chartered Financial Analyst Exams</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Mahfouz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="family">Callanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Sibue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antony</namePart>
<namePart type="family">Papadimitriou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaomo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoţiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, US</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Chartered Financial Analyst (CFA) program is one of the most widely recognized financial certifications globally. In this work, we test a variety of state-of-the-art large language models (LLMs) on mock CFA exams to provide an overview of their financial analysis capabilities using the same evaluation standards applied for human professionals. We benchmark five leading proprietary models and eight open-source models on all three levels of the CFA through challenging multiple-choice and essay questions. We find that flagship proprietary models perform relatively well and can solidly pass levels I and II exams, but fail at level III due to essay questions. Open-source models generally fall short of estimated passing scores, but still show strong performance considering their size, cost, and availability advantages. We also find that using textbook data helps bridge the gap between open-source and proprietary models to a certain extent, despite reduced gains in CFA levels II and III. By understanding the current financial analysis abilities of LLMs, we aim to guide practitioners on which models are best suited for enhancing automation in the financial industry.</abstract>
<identifier type="citekey">mahfouz-etal-2024-state</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-industry.80</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1068</start>
<end>1082</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The State of the Art of Large Language Models on Chartered Financial Analyst Exams
%A Mahfouz, Mahmoud
%A Callanan, Ethan
%A Sibue, Mathieu
%A Papadimitriou, Antony
%A Ma, Zhiqiang
%A Liu, Xiaomo
%A Zhu, Xiaodan
%Y Dernoncourt, Franck
%Y Preoţiuc-Pietro, Daniel
%Y Shimorina, Anastasia
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F mahfouz-etal-2024-state
%X The Chartered Financial Analyst (CFA) program is one of the most widely recognized financial certifications globally. In this work, we test a variety of state-of-the-art large language models (LLMs) on mock CFA exams to provide an overview of their financial analysis capabilities using the same evaluation standards applied for human professionals. We benchmark five leading proprietary models and eight open-source models on all three levels of the CFA through challenging multiple-choice and essay questions. We find that flagship proprietary models perform relatively well and can solidly pass levels I and II exams, but fail at level III due to essay questions. Open-source models generally fall short of estimated passing scores, but still show strong performance considering their size, cost, and availability advantages. We also find that using textbook data helps bridge the gap between open-source and proprietary models to a certain extent, despite reduced gains in CFA levels II and III. By understanding the current financial analysis abilities of LLMs, we aim to guide practitioners on which models are best suited for enhancing automation in the financial industry.
%U https://aclanthology.org/2024.emnlp-industry.80
%P 1068-1082
Markdown (Informal)
[The State of the Art of Large Language Models on Chartered Financial Analyst Exams](https://aclanthology.org/2024.emnlp-industry.80) (Mahfouz et al., EMNLP 2024)
ACL
- Mahmoud Mahfouz, Ethan Callanan, Mathieu Sibue, Antony Papadimitriou, Zhiqiang Ma, Xiaomo Liu, and Xiaodan Zhu. 2024. The State of the Art of Large Language Models on Chartered Financial Analyst Exams. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1068–1082, Miami, Florida, US. Association for Computational Linguistics.