Uncertainty-Aware Financial Risk Analysis and Investment Decision Support Using Retrieval-Augmented Large Language Models and Evidence-Based Reasoning

Authors

  • Tobiasz Ksel Department of Computer Science, University of Central Florida, Orlando, FL, USA.
  • Ryder Strawbridge Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA.

Keywords:

retrieval-augmented generation; financial risk analysis; uncertainty quantification; evidence-based reasoning; decision support; large language models

Abstract

Large language models (LLMs) offer new capabilities for synthesizing financial disclosures, news, and analyst commentary, yet their deployment in risk analysis and investment decision support remains constrained by hallucination, miscalibrated confidence, and weak traceability to source evidence. This paper develops a methodological framework for uncertainty-aware financial risk analysis that couples retrieval-augmented generation (RAG) with evidence-based reasoning and explicit uncertainty quantification. The central contribution is a composite decision-support architecture in which every generated risk claim is linked to a retrievable evidence set, decomposed into aleatoric and epistemic components, and mapped to a calibrated confidence interval that feeds a risk-sensitive investment rule. We formalize the evidence graph, the uncertainty decomposition, a verifiability-weighted generation objective, and a decision-theoretic portfolio adjustment mechanism. The framework clarifies how retrieval quality, source reliability, and disagreement among evidence items propagate into downstream allocation decisions. Analytical results show that evidence-conditioned uncertainty penalties can reduce exposure to unverifiable claims, that the marginal value of additional retrieval diminishes when evidence redundancy is high, and that calibration across evidence cohorts is a necessary condition for trustworthy decision support. The framework provides a technically defensible path from document retrieval to auditable financial risk judgments without requiring unavailable proprietary data or unverified empirical claims.

References

1. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.

2. Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023). Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12), 1–38.

3. Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., van den Driessche, G., Lespiau, J. B., Damoc, B., Clark, A., de Las Casas, D., Guy, A., Menick, J., Ring, R., Hennigan, T., Huang, S., Maggiore, L., Jones, C., Cassirer, A., ... Sifre, L. (2022). Improving language models by retrieving from trillions of tokens. Proceedings of the 39th International Conference on Machine Learning, 162, 2206–2240.

4. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., & Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997.

5. Kendall, A., & Gal, Y. (2017). What uncertainties do we need in Bayesian deep learning for computer vision? Advances in Neural Information Processing Systems, 30, 5574–5584.

6. Gal, Y. (2016). Uncertainty in deep learning (Doctoral dissertation). University of Cambridge.

7. Angelopoulos, A. N., & Bates, S. (2021). A gentle introduction to conformal prediction and distribution-free uncertainty quantification. arXiv preprint arXiv:2107.07511.

8. Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in Neural Information Processing Systems, 30, 6402–6413.

9. Guyatt, G. H., Oxman, A. D., Vist, G. E., Kunz, R., Falck-Ytter, Y., Alonso-Coello, P., & Schünemann, H. J. (2008). GRADE: An emerging consensus on rating quality of evidence and strength of recommendations. BMJ, 336(7650), 924–926.

10. Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77–91.

11. Artzner, P., Delbaen, F., Eber, J. M., & Heath, D. (1999). Coherent measures of risk. Mathematical Finance, 9(3), 203–228.

12. Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020). Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115.

13. Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. Proceedings of the 34th International Conference on Machine Learning, 70, 1321–1330.

14. Karpukhin, V., Oğuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W. (2020). Dense passage retrieval for open-domain question answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 6769–6781.

15. Izacard, G., & Grave, E. (2021). Leveraging passage retrieval with generative models for open domain question answering. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 874–880.

16. Zhang, R. (2025, December). Uncertainty-Aware RAG: Trustworthy Generation and Risk Control. In 2025 5th International Symposium on Artificial Intelligence and Big Data (AIBDF) (pp. 526-531). IEEE.

17. Thorp, E. O. (1969). Optimal gambling systems for favorable games. Revue de l'Institut International de Statistique, 37(3), 273–293.

18. Kahneman, D., & Tversky, A. (1979). Prospect theory: An analysis of decision under risk. Econometrica, 47(2), 263–291.

19. Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The Journal of Finance, 62(3), 1139–1168.

20. Loughran, T., & McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. The Journal of Finance, 66(1), 35–65.

21. Huang, A. H., Lehavy, R., Zang, A. Y., & Zheng, R. (2018). Analyst information discovery and interpretation roles: A topic modeling approach. Management Science, 64(6), 2833–2855.

Downloads

Published

2026-10-09

How to Cite

Tobiasz Ksel, & Ryder Strawbridge. (2026). Uncertainty-Aware Financial Risk Analysis and Investment Decision Support Using Retrieval-Augmented Large Language Models and Evidence-Based Reasoning. Global Financial Analytics Research Review, 3(4). Retrieved from https://www.gfarr.org/index.php/home/article/view/172