Large Language Models in Finance: A Survey
By Yinheng Li, Shaofei Wang, Han Ding, Hang Chen. International Conference on AI in Finance, 2023
471 citations recorded by the source corpus.
Recent advances in large language models (LLMs) have opened new possibilities for artificial intelligence applications in finance. In this paper, we provide a practical survey focused on two key aspects of utilizing LLMs for financial tasks: existing solutions and guidance for adoption. First, we review current approaches employing LLMs in finance, including leveraging pretrained models via zero-shot or few-shot learning, fine-tuning on domain-specific data, and training custom LLMs from scratch. We summarize key models and evaluate their performance improvements on financial natural language processing tasks. Second, we propose a decision framework to guide financial professionals in selecting the appropriate LLM solution based on their use case constraints around data, compute, and performance needs. The framework provides a pathway from lightweight experimentation to heavy investment in customized LLMs. Lastly, we discuss limitations and challenges around leveraging LLMs in financial applications. Overall, this survey aims to synthesize the state-of-the-art and provide a roadmap for responsibly applying LLMs to advance financial AI.
Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Management Science and Operations Research
View Paper: https://www.semanticscholar.org/paper/5432b77bfb1dced97c5b1fc684b0fa7d0d84c424
Citations in the corpus
- Knowledge Conflicts for LLMs: A Survey (2024, unknown): “…and consistency, such as legal document analysis (Shui et al., 2023; Martin et al., 2024), medical diagnosis (Zhou et al., 2023b; Thirunavukarasu et al., 2023), financial analysis (Zhang et al., 2023a; Li et al., 2023e), and educational tools (Caines et al., 2023; Milano et al., 2023), is crucial.”
- A Survey on the Memory Mechanism of Large Language Model-based Agents (2024, unknown): “In addition, cognitive psychology has been studied for a long time, so many effective human memory theories and architectures have been accumulated, which can support more advanced capabilities of the agents [147].”
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning (2025, unknown): “Despite demonstrating remarkable reasoning (Guo et al., 2025) and coding (Guo et al., 2024) capabilities, LLMs (Zhao et al., 2023; Team, 2024; Achiam et al., 2023) often lack domain-specific knowledge (Peng et al., 2023; Li et al., 2023) and are prone to hallucinations (Zhang et al., 2023).”
- ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation (2025, unknown): “1 [11] have received tremendous attention from both industry and academia [17, 26, 36, 39, 48, 66, 68, 82].”