Extracting Financial Data From Unstructured Sources: Leveraging Large Language Models

Huaxia Li; Haoyun Gao; Chengzhang Wu; Miklos A. Vasarhelyi

doi:10.2139/ssrn.4567607

journal article Jan 01, 2023

Extracting Financial Data From Unstructured Sources: Leveraging Large Language Models

Huaxia Li

Haoyun Gao Chengzhang Wu Miklos A. Vasarhelyi

SSRN Electronic Journal · Elsevier BV

View at Publisher Save 10.2139/ssrn.4567607

Topics

No keywords indexed for this article. Browse by subject →

References

67

[1]

A Alaamer "Management accounting in the era of big data" Emerging Trends and Innovation in Business and Finance (2023) 10.1007/978-981-99-6101-6_65

[2]

J L M Altamuro "Corporate integrity culture and compliance: A study of the pharmaceutical industry" Contemporary Accounting Research (2022) 10.1111/1911-3846.12727

[3]

D V Balderas "The Rise of Unstructured Data" Cloudera Blog (2021)

[4]

S W Bauguess The Role of Machine Readability in an AI World. SEC Speeches and Statements (2018)

[5]

E L Beardsley "Street versus GAAP: Which effective tax rate is more informative?" Contemporary Accounting Research (2021) 10.1111/1911-3846.12651

[6]

A W Beck "Opportunistic financial reporting around municipal bond issues" Review of Accounting Studies (2018) 10.1007/s11142-018-9454-2

[7]

R N Bernard Automating Data Extraction with AI (2021)

[8]

K Bochkay "Textual analysis in accounting: What's next?" Contemporary Accounting Research (2023) 10.1111/1911-3846.12825

[9]

T Brown "Language models are few-shot learners" Advances in Neural Information Processing Systems (2020)

[10]

F G Burton "Relevance of accounting research (ROAR) scores: Ratings of titles and abstracts by accounting professionals" Accounting Horizons (2022) 10.2308/horizons-2020-147

[11]

H W Chung Scaling instruction-finetuned language models (2022)

[12]

B P Commerford "Man versus machine: Complex estimates and auditor reliance on artificial intelligence" Journal of Accounting Research (2022) 10.1111/1475-679x.12407

[13]

The Data-Driven Audit: How Automation and AI are Changing the Audit and the Role of the Auditor (2020)

[14]

J S David "The research pyramid: A framework for accounting information systems research" Journal of Information Systems (1999) 10.2308/jis.1999.13.1.7

[15]

S Davidson "Editor's preface" Journal of Accounting Research (1966)

[16]

T De Kok Generative LLMs and textual analysis in accounting: (Chat)GPT as research assistant? (2023)

[17]

C Dowling "A Big 4 firm's use of information technology to control the audit process: How an audit support system is changing auditor behavior" Contemporary Accounting Research (2014) 10.1111/1911-3846.12010

[18]

M El-Haj "Retrieving, classifying and analysing narrative commentary in unstructured (glossy) annual reports published as PDF files" Accounting and Business Research (2020) 10.1080/00014788.2019.1609346

[19]

S A Emett Leveraging ChatGPT for enhancing the internal audit process -A real-world example from a large multinational company (2023)

[20]

M Eulerich A demonstration of how ChatGPT can be used in the internal auditing process (2023)

[21]

T L F�hr Assuring sustainable futures: Auditing sustainability reports using AI foundation models (2023)

[22]

L Gao "PAL: Program-aided language models" Proceedings of the 40th International Conference on Machine Learning (2023)

[23]

G L Geerts "A design science research methodology and its application to accounting information systems research" International Journal of Accounting Information Systems (2011) 10.1016/j.accinf.2011.02.004

[24]

"2023a. Financial Intelligence through Artificial Intelligence" Government Finance Officers Association (GFOA). 2023b. Navigating the Next Frontier: AI's Role in Reshaping Local Governance

[25]

M H Granof "Envisioning the future of government reporting: Looking back to move forward" The CPA Journal (2020)

[26]

S Gregor "Positioning and presenting design science research for maximum impact" MIS Quarterly (2013) 10.25300/misq/2013/37.2.01

[27]

H Gu Artificial intelligence co-piloted auditing (2023)

[28]

Handwiki Social: Comprehensive annual financial report (2022)

[29]

Design Science in Information Systems Research1

Alan R. Hevner, Salvatore T. March, Jinsoo Park et al.

MIS Quarterly 2004 10.2307/25148625

[30]

F D Hodge "The effect of humanizing robo-advisors on investor judgments" Contemporary Accounting Research (2021) 10.1111/1911-3846.12641

[31]

A H Huang "FinBERT: A large language model for extracting information from financial text" Contemporary Accounting Research (2023) 10.1111/1911-3846.12832

[32]

H Issa "AIS research and government accounting research compared: Special section of JETA on the use of AIS technology in government reporting" Journal of Emerging Technologies in Accounting (2018) 10.2308/jeta-10590

[33]

L Jiang "Environmental, social, and governance taxonomy simplification: A hybrid text mining approach" Journal of Emerging Technologies in Accounting (2023) 10.2308/jeta-2022-041

[34]

A G Kim Bloated disclosures: Can ChatGPT help investors process information? (2023)

[35]

A G Kim Context-based interpretation of financial information (2023)

[36]

W J Kim "Overview of U.S. state and local government financial reporting: A reference for academic research" Accounting Horizons (2022) 10.2308/horizons-18-158

[37]

T Kojima "Large language models are zeroshot reasoners" Advances in Neural Information Processing Systems (2022)

[38]

J Krasodomska "Key performance indicators disclosure in the context of the EU directive: When does stakeholder pressure matter?" Meditari Accountancy Research (2020) 10.1108/medar-05-2020-0876

[39]

S K�ster The informational content of key audit matters: Evidence from using artificial intelligence in textual analysis (2023)

[40]

H Li Applying large language models in accounting: A comparative analysis of different methodologies and off-the-shelf examples (2024)

[41]

H Li Addressing the "last mile problem" in open government data: A framework for data extraction from PDF-type governmental reports (2023)

[42]

H Liu "Visual instruction tuning" Advances in Neural Information Processing Systems (2023)

[43]

A Lopez-Lira Can ChatGPT forecast stock price movements? Return predictability and large language models (2023)

[44]

W E Mccarthy "Accounting craftspeople versus accounting seers: Exploring the relevance and innovation gaps in academic accounting research" Accounting Horizons (2012) 10.2308/acch-10313

[45]

S Min Rethinking the role of demonstrations: What makes in-context learning work? (2022)

[46]

N Myers Suggestions for producing and reviewing design science research in accounting (2024)

[47]

A Ng "What LLMs can and cannot do" Coursera (2023)

[48]

D E O'leary "Enterprise large language models: Knowledge characteristics, risks, and organizational activities" Finance and Management (2023)

[49]

; K Openai "A design science research methodology for information systems research" Journal of Management Information Systems (2007) 10.2753/mis0742-1222240302

[50]

S Rajgopal "Integrating practice into accounting research" Management Science (2021) 10.1287/mnsc.2020.3590

Showing 50 of 67 references

Metrics

11

Citations

67

References

Details

Published: Jan 01, 2023

Authors

Cite This Article

Huaxia Li, Haoyun Gao, Chengzhang Wu, et al. (2023). Extracting Financial Data From Unstructured Sources: Leveraging Large Language Models. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4567607

Extracting Financial Data From Unstructured Sources: Leveraging Large Language Models

You May Also Like