Integrating Large Language Models in Financial Investments and Market Analysis: A Survey

Paper: arXiv 2507.01990

Authors: Sedigheh Mahdavi, Jiating, Chen, Pradeep Kumar Joshi, Lina Huertas Guativa, Upmanyu Singh

Abstract

Large Language Models (LLMs) have been employed in financial decision making, enhancing analytical capabilities for investment strategies. Traditional investment strategies often utilize quantitative models, fundamental analysis, and technical indicators. However, LLMs have introduced new capabilities to process and analyze large volumes of structured and unstructured data, extract meaningful insights, and enhance decision-making in real-time. This survey provides a structured overview of recent research on LLMs within the financial domain, categorizing research contributions into four main frameworks: LLM-based Frameworks and Pipelines, Hybrid Integration Methods, Fine-Tuning and Adaptation Approaches, and Agent-Based Architectures. This study provides a structured review of recent LLMs research on applications in stock selection, risk assessment, sentiment analysis, trading, and financial forecasting. By reviewing the existing literature, this study highlights the capabilities, challenges, and potential directions of LLMs in financial markets.

Complexity vs Empirical Score

• Math Complexity: 2.0/10
• Empirical Rigor: 5.0/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: This paper is a literature survey covering the integration of Large Language Models (LLMs) in finance, categorizing approaches into four main frameworks. It contains minimal mathematical derivations, focusing instead on high-level taxonomy, empirical applications, and qualitative comparisons of recent models and pipelines.

Research Flowchart

  flowchart TD
    A["Research Goal: Survey LLM Integration in Financial Investments"] --> B["Data Collection: Financial Text, Market Data & Literature"]
    B --> C["Categorization into 4 Core LLM Frameworks"]
    C --> D["Analysis of Key Financial Tasks"]
    D --> E["Evaluation of Challenges & Future Directions"]
    E --> F["Outcome: Comprehensive Taxonomy for LLM-Based Finance"]