Integration of Large Language Models in Mobile Applications for Statutory Auditing and Finance

Autores/as

  • Sergio Robles Serrano
  • Jesus Rios Perez
  • Germán Sánchez Torres Universidad del Magdalena

DOI:

https://doi.org/10.15665/rp.v22i1.3334

Palabras clave:

Inteligencia Artificial, revisoría fiscal, búsqueda semántica, Voice Interaction Community Group, grandes modelos de lenguaje

Resumen

In the current digital age, Artificial Intelligence, with an emphasis on large language models, has gained prominence in various fields such as finance and tax auditing, offering greater efficiency and accuracy in accessing information. This study proposes a software architecture for a mobile application as an intelligent personal assistant in this domain, integrating semantic search and large language models to optimize responses. The methodology included a literature review and a focus on emerging technologies through a technological surveillance study, culminating in an architecture inspired by the Voice Interaction Community Group of the W3C, adapted for non-intent based models with LLM. After developing the application, corporate data was integrated, facilitating semantic searches using a dense passage retrieval scheme and integrating it with language models. The results showed increased efficiency in obtaining financial and tax information and more contextual responses, speeding up data retrieval. This indicates that such integrations can revolutionize how professionals access information. However, it is essential to address ethical, security, and privacy aspects to ensure the reliability and sustained adoption of these tools.

Biografía del autor/a

Germán Sánchez Torres, Universidad del Magdalena

Identificador ORCID
Guardar

Citas

B. Huang, «On the Practical Application of Computer Technology in Finance and Tax Audit», J. Phys.: Conf. Ser., vol. 1744, n.o 3, p. 032042, feb. 2021, doi: 10.1088/1742-6596/1744/3/032042.

G. S. Jayesh, D. Novaliendry, S. K. Gupta, A. K. Sharma, y B. Hazela, «A Comprehensive Analysis of Technologies for Accounting and Finance in Manufacturing Firms», ECS Trans., vol. 107, n.o 1, p. 2715, abr. 2022, doi: 10.1149/10701.2715ecst.

B. Adi̇loglu y N. Gungor, «THE IMPACT OF DIGITALIZATION ON THE AUDIT PROFESSION: A REVIEW OF TURKISH INDEPENDENT AUDIT FIRMS», JBEF, vol. 8, n.o 4, Art. n.o 4, dic. 2019.

S. Patel, Y.-T. Chiu, M. S. Khan, J.-G. Bernard, y T. A. T. Ekandjo, «Conversational Agents in Organisations: Strategic Applications and Implementation Considerations», JGIM, vol. 29, n.o 6, pp. 1-25, nov. 2021, doi: 10.4018/JGIM.20211101.oa53.

L. Nuñez Aguilar, «SISTEMA IVR PARA LA MEJORA DE LA GESTION DE COBRANZA DE LA EMPRESA CONSORCIO DE TECNOLOGÍA E INNOVACIÓN S.A.C., JAÉN 2017», Repositorio Institucional - USS, 2018, Accedido: 3 de septiembre de 2023. [En línea]. Disponible en: http://repositorio.uss.edu.pe//handle/20.500.12802/5081

F. Huseynov, «Chatbots in Digital Marketing: Enhanced Customer Experience and Reduced Customer Service Costs», en Contemporary Approaches of Digital Marketing and the Role of Machine Intelligence, IGI Global, 2023, pp. 46-72. doi: 10.4018/978-1-6684-7735-9.ch003.

K. S. Carranza Rodríguez y G. M. Carranza rodríguez, «Sistema de Información para el proceso de Gestión de Cobranzas de carteras morosas en la empresa Crédito y Cobranzas SAC. ChiclayoLambayeque», may 2018, Accedido: 3 de septiembre de 2023. [En línea]. Disponible en: http://repositorio.unprg.edu.pe/handle/20.500.12893/1864

Y. Y. Lopez Vitor y R. C. Rojas Hilario, «Asistente virtual para el seguimiento de cobranza en una empresa de envases metálicos usando lenguaje natural», Universidad Peruana de Ciencias Aplicadas (UPC), sep. 2021, Accedido: 3 de septiembre de 2023. [En línea]. Disponible en: https://repositorioacademico.upc.edu.pe/handle/10757/658517

H. Lee, Voice User Interface Projects: Build voice-enabled applications using Dialogflow for Google Home and Alexa Skills Kit for Amazon Echo. Packt Publishing Ltd, 2018.

M. J. Sánchez-Franco, F. J. Arenas-Márquez, y M. Alonso-Dos-Santos, «Using structural topic modelling to predict users’ sentiment towards intelligent personal agents. An application for Amazon’s echo and Google Home», Journal of Retailing and Consumer Services, vol. 63, p. 102658, nov. 2021, doi: 10.1016/j.jretconser.2021.102658.

T. Lau y B. Leimer, «The era of connectedness: How AI will help deliver the future of banking», Journal of Digital Banking, vol. 3, n.o 3, pp. 215-231, ene. 2019.

A. Anand, V. V, A. Anand, y V. Setty, «Query Understanding in the Age of Large Language Models». arXiv, 28 de junio de 2023. doi: 10.48550/arXiv.2306.16004.

P. D. 29 N. 2019 |Updated: 29-N.-2019 |Category: O. |Author: W. |Member L. Gold |Points: 0 |, «The 12 Advantages and Disadvantages of Voice User Interface», Techulator, 29 de noviembre de 2019. https://www.techulator.com/resources/18784-the-12-advantages-and-disadvantages-of-voice-user-interface (accedido 29 de noviembre de 2022).

J. Kiseleva, K. Williams, A. Hassan Awadallah, A. C. Crook, I. Zitouni, y T. Anastasakos, «Predicting User Satisfaction with Intelligent Assistants», en Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, en SIGIR ’16. New York, NY, USA: Association for Computing Machinery, jul. 2016, pp. 45-54. doi: 10.1145/2911451.2911521.

S. A. Khowaja, P. Khuwaja, y K. Dev, «ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review». arXiv, 13 de abril de 2023. doi: 10.48550/arXiv.2305.03123.

V. Karpukhin et al., «Dense Passage Retrieval for Open-Domain Question Answering». arXiv, 30 de septiembre de 2020. doi: 10.48550/arXiv.2004.04906.

D. S. Sachan et al., «Improving Passage Retrieval with Zero-Shot Question Generation». arXiv, 2 de abril de 2023. doi: 10.48550/arXiv.2204.07496.

X. Ma, M. Li, K. Sun, J. Xin, y J. Lin, «Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval», en Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online and Punta Cana, Dominican Republic: Association for Computational Linguistics, nov. 2021, pp. 2854-2859. doi: 10.18653/v1/2021.emnlp-main.227.

Y. Wang, H. Ma, y D. Z. Wang, «LIDER: An Efficient High-dimensional Learned Index for Large-scale Dense Passage Retrieval». arXiv, 9 de octubre de 2022. doi: 10.48550/arXiv.2205.00970.

F. O. Cruz?Páez y O. Vanegas?Flórez, «Vigilancia tecnológica, inteligencia competitiva y cultura organizacional universidad de Cundinamarca Facatativá [1]», Política, Globalidad y Ciudadanía, vol. 6, n.o 12, pp. 84-101, 2020.

B. Fernandez, S. Pérez, y F. Del-Valle-Gastaminza, «Metodología para la implantación de sistemas de vigilancia tecnológica y documental: El caso del proyecto INREDIS», Investigación bibliotecológica, vol. 23, pp. 149-177, dic. 2009, doi: 10.22201/iibi.0187358xp.2009.49.21393.

P. M. Ortega, «Vigilancia e inteligencia competitiva: fundamentos e implicaciones», Revista madri+d. Monografía: revista de investigación en gestión de la innovación y tecnología, n.o 7 (Agosto), pp. 15-22, 2003.

A. Nosella, G. Petroni, y R. Salandra, «Technological change and technology monitoring process: Evidence from four Italian case studies», Journal of Engineering and Technology Management, vol. 25, pp. 321-337, dic. 2008, doi: 10.1016/j.jengtecman.2008.10.001.

L. Rey, «Informe APEI sobre vigilancia tecnológica», Informes APEI, No. 4, 2009, ISBN 978-84-692-7999-1, dic. 2009.

W. Seymour y J. Such, «Ignorance is Bliss? The Effect of Explanations on Perceptions of Voice Assistants», Proc. ACM Hum.-Comput. Interact., vol. 7, n.o CSCW1, p. 64:1-64:24, abr. 2023, doi: 10.1145/3579497.

M. Tabassum et al., «Investigating Users’ Preferences and Expectations for Always-Listening Voice Assistants», Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 3, n.o 4, p. 153:1-153:23, sep. 2020, doi: 10.1145/3369807.

L. Mirghaderi, M. Sziron, y E. Hildt, «Investigating user perceptions of commercial virtual assistants: A qualitative study», Frontiers in Psychology, vol. 13, 2022, Accedido: 3 de septiembre de 2023. [En línea]. Disponible en: https://www.frontiersin.org/articles/10.3389/fpsyg.2022.944714

A. Mishra, A. Shukla, y S. K. Sharma, «Psychological determinants of users’ adoption and word-of-mouth recommendations of smart voice assistants», International Journal of Information Management, vol. 67, p. 102413, dic. 2022, doi: 10.1016/j.ijinfomgt.2021.102413.

S. K. Sharma, R. De, A. Jeyaraj, y R. Raman, «Guest editorial: Re-imagining diffusion and adoption of emerging technologies», International Journal of Information Management, vol. 67, p. 102541, dic. 2022, doi: 10.1016/j.ijinfomgt.2022.102541.

A. Farooq, D. Jeske, P. van Schaik, y M. Moran, «Voice Assistants: (Physical) Device Use Perceptions, Acceptance, and Privacy Concerns», en The Role of Digital Technologies in Shaping the Post-Pandemic World, S. Papagiannidis, E. Alamanos, S. Gupta, Y. K. Dwivedi, M. Mäntymäki, y I. O. Pappas, Eds., en Lecture Notes in Computer Science. Cham: Springer International Publishing, 2022, pp. 485-498. doi: 10.1007/978-3-031-15342-6_37.

D. Pal, M. D. Babakerkhell, y X. Zhang, «Exploring the Determinants of Users’ Continuance Usage Intention of Smart Voice Assistants», IEEE Access, vol. 9, pp. 162259-162275, 2021, doi: 10.1109/ACCESS.2021.3132399.

«Voice Interaction Community Group», 16 de junio de 2020. https://www.w3.org/community/voiceinteraction/ (accedido 2 de septiembre de 2023).

«W3C», W3C. https://www.w3.org/ (accedido 3 de septiembre de 2023).

«Intelligent Personal Assistant Interfaces». https://w3c.github.io/voiceinteraction/voice%20interaction%20drafts/paInterfaces/paInterfaces.htm (accedido 3 de septiembre de 2023).

A. Agarwal, S. Gawade, A. P. Azad, y P. Bhattacharyya, «KITLM: Domain-Specific Knowledge InTegration into Language Models for Question Answering». arXiv, 7 de agosto de 2023. doi: 10.48550/arXiv.2308.03638.

A. Halevy y J. Dwivedi-Yu, «Learnings from Data Integration for Augmented Language Models». arXiv, 10 de abril de 2023. doi: 10.48550/arXiv.2304.04576.

Z. Luo et al., «Augmented Large Language Models with Parametric Knowledge Guiding». arXiv, 18 de mayo de 2023. doi: 10.48550/arXiv.2305.04757.

M. T. R. Laskar, M. S. Bari, M. Rahman, M. A. H. Bhuiyan, S. Joty, y J. X. Huang, «A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets». arXiv, 5 de julio de 2023. doi: 10.48550/arXiv.2305.18486.

F. Lashkari, E. Bagheri, y A. A. Ghorbani, «Neural embedding-based indices for semantic search», Information Processing & Management, vol. 56, n.o 3, pp. 733-755, may 2019, doi: 10.1016/j.ipm.2018.10.015.

H. Zamani y W. B. Croft, «Estimating Embedding Vectors for Queries», en Proceedings of the 2016 ACM International Conference on the Theory of Information Retrieval, en ICTIR ’16. New York, NY, USA: Association for Computing Machinery, sep. 2016, pp. 123-132. doi: 10.1145/2970398.2970403.

K. N. R. K. R. Alluri y A. K. Vuppala, «Chapter 7 - A study on the emotional state of a speaker in voice bio-metrics», en Advances in Ubiquitous Computing, A. Neustein, Ed., en Advances in ubiquitous sensing applications for healthcare. Academic Press, 2020, pp. 223-236. doi: 10.1016/B978-0-12-816801-1.00007-4.

H. Liu, «Chapter 1 - Introduction», en Robot Systems for Rail Transit Applications, H. Liu, Ed., Elsevier, 2020, pp. 1-36. doi: 10.1016/B978-0-12-822968-2.00001-2.

J. P. Campbell, W. M. Campbell, A. V. McCree, C. J. Weinstein, y S. M. Lewandowski, «Chapter 10 - Cognitive Services for the User», en Cognitive Radio Technology (Second Edition), B. A. Fette, Ed., Oxford: Academic Press, 2009, pp. 305-324. doi: 10.1016/B978-0-12-374535-4.00010-2.

Descargas

Publicado

2024-03-02

Número

Sección

Articles