A Practical Analysis of Large Language Models Empowering Investment Management from the Financial Text Perspective
DOI:
https://doi.org/10.54691/6awmpb58Keywords:
Large language models, financial text, investment management, textual analysis, retrieval-augmented generation, model riskAbstract
This paper investigates how large language models can assist in investment management through the processing of financial text. It is a discussion of ideas and applications, not an empirical investigation, and no original datasets, backtests, portfolios or performance data have been provided. The development path from dictionary-based textual indicators to Transformers, domain-adapted language models and retrieval-assisted workflows is presented. Next, it presents some applications of research-intake systems, document comparison, event extraction, risk monitoring, investment-memo drafting and client communication. Pay attention to the evidence supporting the results of the model. Although the generated summary and classification can increase the efficiency of the workflow, they are not verified facts, forecasts or investment recommendations unless supported by official data and professional reviews. A controlled operating model based on source provenance, retrieval, structured prompts, numerical verification, human approval, access control, audit log and continuous evaluation is proposed in this paper. Therefore, large language models are more suitable for the applications of supervised analysis interfaces than for autonomous portfolio management systems.
Downloads
References
[1] 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. https://doi.org/10.1111/j.1540 6261.2007.01232.x DOI: https://doi.org/10.1111/j.1540-6261.2007.01232.x
[2] 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. https://doi.org/10.1111/j.1540 6261.2010.01625.x DOI: https://doi.org/10.1111/j.1540-6261.2010.01625.x
[3] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008.
[4] Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre training of deep bidirectional transformers for language understanding. In Proceedings of NAACL HLT 2019 (pp. 4171–4186). https://doi.org/10.18653/v1/N19 1423 DOI: https://doi.org/10.18653/v1/N19-1423
[5] Araci, D. (2019). FinBERT: Financial sentiment analysis with pre trained language models. arXiv:1908.10063. https://doi.org/10.48550/arXiv.1908.10063
[6] Brown, T. B., Mann, B., Ryder, N., et al. (2020). Language models are few shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
[7] Wu, S., Irsoy, O., Lu, S., et al. (2023). BloombergGPT: A large language model for finance. arXiv:2303.17564. https://doi.org/10.48550/arXiv.2303.17564
[8] Yang, H., Liu, X.-Y., & Wang, C. D. (2023). FinGPT: Open source financial large language models. arXiv:2306.06031. https://doi.org/10.48550/arXiv.2306.06031 DOI: https://doi.org/10.2139/ssrn.4489826
[9] Islam, P., Kannappan, A., Kiela, D., Qian, R., Scherrer, N., & Vidgen, B. (2023). FinanceBench: A new benchmark for financial question answering. arXiv:2311.11944. https://doi.org/10.48550/arXiv.2311.11944
[10] Lopez Lira, A., & Tang, Y. (2023). Can ChatGPT forecast stock price movements? Return predictability and large language models. arXiv:2304.07619. https://doi.org/10.48550/arXiv.2304.07619 DOI: https://doi.org/10.2139/ssrn.4412788
[11] National Institute of Standards and Technology. (2023). Artificial Intelligence Risk Management Framework (AI RMF 1.0) (NIST AI 100 1). https://doi.org/10.6028/NIST.AI.100 1
[12] U.S. Securities and Exchange Commission. (2023). Conflicts of interest associated with the use of predictive data analytics by broker dealers and investment advisers (Release Nos. 34 97990; IA 6353). https://www.sec.gov/files/rules/proposed/2023/34 97990.pdf
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Academic Journal of Finance and Accounting

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.







