Paper: arXiv 2311.10723

Authors: Yinheng Li, Shaofei Wang, Han Ding, Hang Chen

Abstract

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.

Complexity vs Empirical Score

  • Math Complexity: 2.0/10
  • Empirical Rigor: 4.5/10
  • Quadrant: Philosophers — conceptual discussion, limited math and data

Why this score: This paper is a comprehensive survey paper providing a practical overview and decision framework for adopting LLMs in finance without introducing new mathematical models or empirical backtesting. It excels in clarity and completeness as a literature review, making it a valuable reference guide for practitioners despite the lack of technical math density.

Research Flowchart

  flowchart TD
    A[Research Goal: Survey & Roadmap for LLMs in Finance] --> B[Review Existing Financial LLM Solutions]
    
    B --> C[Categorize Approaches: Pretrained, Fine-Tuned, Custom Models]
    B --> D[Evaluate Performance on Financial NLP Tasks]
    
    C & D --> E[Develop Decision Framework for Model Adoption]
    
    E --> F[Identify Limitations & Challenges in Financial AI]
    
    F --> G[Outcomes: SOTA Synthesis & Responsible Adoption Roadmap]