國立虎尾科技大學 |

Exploring the Frontier of Artificial Intelligence Applications in Accounting and Auditing : = Three Essays on Foundation Model Implementations With Emphasis on Large Language Models.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Exploring the Frontier of Artificial Intelligence Applications in Accounting and Auditing :/
其他題名:	Three Essays on Foundation Model Implementations With Emphasis on Large Language Models.
作者:	Gu, Hanchi.
面頁冊數:	1 online resource (173 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
Contained By:	Dissertations Abstracts International86-01B.
標題:	Language. -
電子資源:	click for full text (PQDT)
ISBN:	9798383570258

Exploring the Frontier of Artificial Intelligence Applications in Accounting and Auditing : = Three Essays on Foundation Model Implementations With Emphasis on Large Language Models.
Gu, Hanchi.

Exploring the Frontier of Artificial Intelligence Applications in Accounting and Auditing :Three Essays on Foundation Model Implementations With Emphasis on Large Language Models. - 1 online resource (173 pages)

Source: Dissertations Abstracts International, Volume: 86-01, Section: B.

Thesis (Ph.D.)--Rutgers The State University of New Jersey, Graduate School - Newark, 2024.

Includes bibliographical references

This dissertation delves into the integration of foundation models in accounting and auditing, showcasing their potential to revolutionize the field.The first essay explores the abilities, mechanisms, and implications of Large Language Models (LLMs) within the accounting domain. First, this study demonstrates LLMs' abilities, then discusses selected mechanisms crucial for the accounting community and their practical implications. Furthermore, this chapter analyzes the lifecycle of LLM research, outlining their role in developing sophisticated accounting systems. The proposed lifecycle analysis can be generalized to encompass other technologies that hold the potential for developing a variety of systems. This chapter serves as a basis for the knowledge presented in the following two chapters.The second essay proposes the concept of artificial intelligence co-piloted auditing, emphasizing the collaborative potential of auditors and foundation models in the auditing domain. Auditors' capabilities are enhanced through artificial intelligence in a variety of audit tasks. To exemplify the potential of this co-piloted audit paradigm, this paper illustrates a systematic fine-tuning approach of foundation models using chain-of-thought prompting that enables instruction learning, in-context learning, and sequential reasoning. The chapter provides a detailed description of the formulated prompt protocols and the corresponding responses from the model in different tasks. The findings underscore the transformative role of foundation models in reshaping the future of auditing and advocate for continued exploration in this area.The third essay proposes a future version of AI-based multimodal auditing in practice. Taking advantage of foundation models' potential in multimodal data integration, data of different modalities are connected automatically. Tabular, textual, image, and other formats of data are integrated into one system. Auditors can use natural languages to give instructions and finish diverse audit tasks. The paper then designs a methodology with a prompt template and implementation strategy for multimodal tasks. This chapter evaluates the feasibility of the idea through the designed zero-shot prompting application to a simulation case study with five experiments. The result shows the latest LLMs can complete the five audit-related tasks, proving the feasibility of developing an auditing system for multimodal data leveraging foundation models.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798383570258Subjects--Topical Terms:

571568
Language.
Subjects--Index Terms:

Accounting information systemsIndex Terms--Genre/Form:

554714
Electronic books.

Exploring the Frontier of Artificial Intelligence Applications in Accounting and Auditing : = Three Essays on Foundation Model Implementations With Emphasis on Large Language Models.
LDR:04080ntm a22004217 4500 001 1151914
005 20241118135906.5
006 m o d
007 cr mn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798383570258
035 $a (MiAaPQ)AAI31243425
035 $a AAI31243425
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Gu, Hanchi. $3 1478757
245 1 0 $a Exploring the Frontier of Artificial Intelligence Applications in Accounting and Auditing : $b Three Essays on Foundation Model Implementations With Emphasis on Large Language Models.
264 0 $c 2024
300 $a 1 online resource (173 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
500 $a Advisor: Vasarhelyi, Miklos A.
502 $a Thesis (Ph.D.)--Rutgers The State University of New Jersey, Graduate School - Newark, 2024.
504 $a Includes bibliographical references
520 $a This dissertation delves into the integration of foundation models in accounting and auditing, showcasing their potential to revolutionize the field.The first essay explores the abilities, mechanisms, and implications of Large Language Models (LLMs) within the accounting domain. First, this study demonstrates LLMs' abilities, then discusses selected mechanisms crucial for the accounting community and their practical implications. Furthermore, this chapter analyzes the lifecycle of LLM research, outlining their role in developing sophisticated accounting systems. The proposed lifecycle analysis can be generalized to encompass other technologies that hold the potential for developing a variety of systems. This chapter serves as a basis for the knowledge presented in the following two chapters.The second essay proposes the concept of artificial intelligence co-piloted auditing, emphasizing the collaborative potential of auditors and foundation models in the auditing domain. Auditors' capabilities are enhanced through artificial intelligence in a variety of audit tasks. To exemplify the potential of this co-piloted audit paradigm, this paper illustrates a systematic fine-tuning approach of foundation models using chain-of-thought prompting that enables instruction learning, in-context learning, and sequential reasoning. The chapter provides a detailed description of the formulated prompt protocols and the corresponding responses from the model in different tasks. The findings underscore the transformative role of foundation models in reshaping the future of auditing and advocate for continued exploration in this area.The third essay proposes a future version of AI-based multimodal auditing in practice. Taking advantage of foundation models' potential in multimodal data integration, data of different modalities are connected automatically. Tabular, textual, image, and other formats of data are integrated into one system. Auditors can use natural languages to give instructions and finish diverse audit tasks. The paper then designs a methodology with a prompt template and implementation strategy for multimodal tasks. This chapter evaluates the feasibility of the idea through the designed zero-shot prompting application to a simulation case study with five experiments. The result shows the latest LLMs can complete the five audit-related tasks, proving the feasibility of developing an auditing system for multimodal data leveraging foundation models.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Language. $3 571568
650 4 $a Computer engineering. $3 569006
650 4 $a Finance. $3 559073
653 $a Accounting information systems
653 $a Auditing
653 $a Foundation model
653 $a Large Language Models
653 $a AI-based multimodal auditing
655 7 $a Electronic books. $2 local $3 554714
690 $a 0272
690 $a 0464
690 $a 0679
690 $a 0800
690 $a 0508
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Rutgers The State University of New Jersey, Graduate School - Newark. $b Management. $3 1468083
773 0 $t Dissertations Abstracts International $g 86-01B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31243425 $z click for full text (PQDT)