A Review of Large Language Models for Stock Price Forecasting from a Hedge-Fund Perspective

Paper: arXiv 2605.05211

Authors: Olivia Zhang, Zhilin Zhang

Abstract

Large language models (LLMs) are increasingly deployed in quantitative finance for stock price forecasting. This review synthesizes recent applications of LLMs in this domain, including extracting sentiment from financial news and social media, analyzing financial reports and earnings-call transcripts, tokenizing or symbolizing stock price series, and constructing multi-agent trading systems. Particular attention is paid to practical pitfalls that are often understated in the literature, such as fragility in sentiment analysis, dataset and horizon design, performance evaluation metrics, data leakage, illiquidity premia, and limits of stock price predictability. Organized from a hedge-fund perspective, the review is intended to guide both academic researchers and hedge fund managers in integrating LLMs into real-world trading pipelines and in stress-testing their robustness under realistic market frictions.

Complexity vs Empirical Score

• Math Complexity: 2.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: This paper provides a thorough, practical survey of LLM applications in stock forecasting from a real-world hedge fund perspective. While light on deep mathematical formalisms, it excels in highlighting practical market frictions, data leakage risks, and evaluation pitfalls often overlooked in purely academic literature.

Research Flowchart

  flowchart TD
    A["Research Goal: Synthesize LLM applications & pitfalls in stock forecasting"] --> B["Data Inputs: News, Social Media, Financial Reports & Price Series"]
    B --> C["Core Methodologies: Sentiment Analysis, Text Mining & Multi-Agent Systems"]
    C --> D["Evaluate Practical Pitfalls & Market Frictions"]
    D --> E["Outcomes: Robust LLM Trading Pipelines & Stress-Testing Frameworks"]