Bridging finance and AI: a comprehensive survey of large language models in financial system

Ameer Tamoor Khan (), Shuai Li () and Xinwei Cao ()
Additional contact information
Ameer Tamoor Khan: University of Copenhagen
Shuai Li: University of Oulu
Xinwei Cao: Jiangnan University

Digital Finance, 2025, vol. 7, issue 4, No 4, 679-701

Abstract: Abstract Large Language Models (LLMs) are reshaping financial analytics, enabling automated summarization, sentiment analysis, numerical reasoning, and decision support. In this survey, we provide a clear and structured overview of LLM adoption in finance. We introduce a taxonomy of key tasks, including text processing, forecasting, and question answering, and review core architectures and adaptation strategies for both general-purpose and finance-specific LLMs. We compare performance trade-offs across models, examine evaluation metrics relevant to financial applications, and discuss deployment challenges such as data privacy, bias, and explainability. Our multi-level adoption framework offers practical guidance for balancing accuracy, cost, and privacy across institutions. Finally, we outline future research opportunities, including cross-lingual modeling, symbolic reasoning, and open finance benchmarks. This survey aims to help researchers and practitioners responsibly leverage LLMs for more transparent, effective, and inclusive financial AI.

Keywords: Large language models; Financial natural language processing; Transformer architectures; Finance-specific benchmarks; Ethical and regulatory considerations (search for similar items in EconPapers)
JEL-codes: C45 D83 G14 G17 G18 O33 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42521-025-00146-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:digfin:v:7:y:2025:i:4:d:10.1007_s42521-025-00146-3

Ordering information: This journal article can be ordered from
https://www.springer.com/finance/journal/42521

DOI: 10.1007/s42521-025-00146-3

Access Statistics for this article

Digital Finance is currently edited by Wolfgang Karl Härdle, Steven Kou and Min Dai

More articles in Digital Finance from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().