Document Open Access Logo

Trustworthy Generative AI for Financial Services (Practitioner Track)

Authors Marc-André Zöller , Anastasiia Iurshina , Ines Röder

PDF
Thumbnail PDF

File

OASIcs.SAIA.2024.2.pdf
  • Filesize: 445 kB
  • 5 pages

Document Identifiers

Author Details

Marc-André Zöller
  • GFT Deutschland GmbH, Eschborn, Germany
Anastasiia Iurshina
  • GFT Deutschland GmbH, Stuttgart, Germany
Ines Röder
  • GFT Deutschland GmbH, Stuttgart, Germany

Cite As Get BibTex

Marc-André Zöller, Anastasiia Iurshina, and Ines Röder. Trustworthy Generative AI for Financial Services (Practitioner Track). In Symposium on Scaling AI Assessments (SAIA 2024). Open Access Series in Informatics (OASIcs), Volume 126, pp. 2:1-2:5, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025) https://doi.org/10.4230/OASIcs.SAIA.2024.2

Abstract

This work introduces GFT EnterpriseGPT, a regulatory-compliant, trustworthy generative AI (GenAI) platform tailored for the financial services sector. We discuss the unique challenges of applying GenAI in highly regulated environments. In the financial sector data privacy, ethical considerations, and regulatory compliance are paramount. Our solution addresses these challenges through multi-level safeguards, including robust guardrails, privacy-preserving techniques, and grounding mechanisms. Robust guardrails prevent unsafe inputs and outputs, and privacy-preserving techniques reduce the need for data transmission to third-party providers. In contrast, grounding mechanisms ensure the accuracy and reliability of artificial intelligence (AI) generated content. By incorporating these measures, we propose a path forward for safely harnessing the transformative potential of GenAI in finance, ensuring reliability, transparency, and adherence to ethical and regulatory standards. We demonstrate the practical application of GFT EnterpriseGPT within a large-scale financial institution, where it successfully improves operational efficiency and compliance.

Subject Classification

ACM Subject Classification
  • Applied computing → Online banking
  • Applied computing → Document management and text processing
  • Human-centered computing → Collaborative and social computing
  • Computing methodologies → Artificial intelligence
Keywords
  • Generative AI
  • GenAI
  • Trustworthy AI
  • Finance
  • Guardrails
  • Grounding

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

References

  1. Landesbank Baden-Würtemberg. Lbbw startet mit eigener generativer ki-lösung durch, April 2024. [Online; accessed 26-July-2024]. URL: https://www.lbbw.de/artikelseite/pressemitteilung/lbbw-startet-mit-eigener-generativer-ki-loesung-durch_ah8wecz4u8_d.html.
  2. Erik Brynjolfsson, Danielle Li, and Lindsey R Raymond. Generative ai at work. Working Paper 31161, National Bureau of Economic Research, April 2023. URL: https://doi.org/10.3386/w31161.
  3. Zhichen Dong, Zhanhui Zhou, Chao Yang, Jing Shao, and Yu Qiao. Attacks, defenses and evaluations for llm conversation safety: A survey. arXiv preprint arXiv:2402.09283, 2024. URL: https://doi.org/10.48550/arXiv.2402.09283.
  4. J. Galindo and P. Tamayo. Credit risk assessment using statistical and machine learning: Basic methodology and risk modeling applications. Computational Economics, 15(1):107-143, April 2000. URL: https://doi.org/10.1023/A:1008699112516.
  5. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. arXiv preprint arXiv:2311.05232, 2023. URL: https://doi.org/10.48550/arXiv.2311.05232.
  6. Zengyi Huang, Chang Che, Haotian Zheng, and Chen Li. Research on generative artificial intelligence for virtual financial robo-advisor. Academic Journal of Science and Technology, 10(1):74-80, March 2024. URL: https://doi.org/10.54097/30r2kk80.
  7. Colin Jarvis. How to implement llm guardrails?, December 2023. [Online; accessed 03-September-2024]. URL: https://cookbook.openai.com/examples/how_to_use_guardrails.
  8. Krishnaram Kenthapadi, Mehrnoosh Sameki, and Ankur Taly. Grounding and evaluation for large language models: Practical challenges and lessons learned (survey). In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 6523-6533. Association for Computing Machinery, 2024. URL: https://doi.org/10.1145/3637528.3671467.
  9. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. Retrieval-augmented generation for knowledge-intensive nlp tasks. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 9459-9474. Curran Associates, Inc., 2020. Google Scholar
  10. Bahar Memarian and Tenzin Doleck. Fairness, accountability, transparency, and ethics (fate) in artificial intelligence (ai) and higher education: A systematic review. Computers and Education: Artificial Intelligence, 5:100152, 2023. URL: https://doi.org/10.1016/j.caeai.2023.100152.
  11. Microsoft. What is provisioned throughput?, May 2024. [Online; accessed 30-July-2024]. URL: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/provisioned-throughput.
  12. Rafet Sifa, Anna Ladi, Maren Pielka, Rajkumar Ramamurthy, Lars Hillebrand, Birgit Kirsch, David Biesner, Robin Stenzel, Thiago Bell, Max Lübbering, Ulrich Nütten, Christian Bauckhage, Ulrich Warning, Benedikt Fürst, Tim Dilmaghani Khameneh, Daniel Thom, Ilgar Huseynov, Roland Kahlert, Jennifer Schlums, Hisham Ismail, Bernd Kliem, and Rüdiger Loitz. Towards automated auditing with machine learning. In Proceedings of the ACM Symposium on Document Engineering 2019, DocEng '19, New York, NY, USA, 2019. Association for Computing Machinery. URL: https://doi.org/10.1145/3342558.3345421.
  13. Peng Sun, Xuezhen Yang, Xiaobing Zhao, and Zhijuan Wang. An overview of named entity recognition. In 2018 International Conference on Asian Language Processing (IALP), pages 273-278, 2018. URL: https://doi.org/10.1109/IALP.2018.8629225.
  14. Ehsan Toreini, Mhairi Aitken, Kovila Coopamootoo, Karen Elliott, Carlos Gonzalez Zelaya, and Aad van Moorsel. The relationship between trust in ai and trustworthy machine learning technologies. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, FAT* '20, pages 272-283, New York, NY, USA, 2020. Association for Computing Machinery. URL: https://doi.org/10.1145/3351095.3372834.
  15. Neeraj Varshney, Pavel Dolin, Agastya Seth, and Chitta Baral. The art of defending: A systematic evaluation and analysis of llm defense strategies on safety and over-defensiveness. arXiv preprint arXiv:2401.00287, 2023. Google Scholar
  16. Sreedhar Yalamati. Data privacy, compliance, and security in cloud computing for finance. In Practical Applications of Data Processing, Algorithms, and Modeling, pages 127-144. IGI Global, 2024. URL: https://doi.org/10.4018/979-8-3693-2909-2.ch010.
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact