Large Language Models for Financial and Investment Management: Applications and Benchmarks

The rapid evolution and unprecedented advancements in large language models (LLMs) have ushered in a new era of innovation in the realm of machine learning, with far-reaching implications for the finance and investment management sectors. These models have exhibited remarkable prowess in contextual understanding, processing vast and complex datasets, and generating content that aligns closely with human preferences. The transformative potential of LLMs in finance has catalyzed a surge of research and applications. As the integration of LLMs into financial practices continues to accelerate, there is an urgent need for a systematic examination of their diverse applications, methodologies, and impact, which necessitates a comprehensive review and synthesis of recent developments in this rapidly evolving field. This article aims to bridge the gap between cutting-edge artificial intelligence technology and its practical implementation in finance, providing a robust framework for understanding and leveraging LLMs in financial contexts. The authors explore the application of LLMs on various financial tasks, focusing on their potential to transform traditional practices and drive innovation. The article is highlighted for categorizing the existing literature into key application areas, including linguistic tasks, sentiment analysis, financial time series, financial reasoning, and agent-based modeling. For each application area, the authors delve into specific methodologies, such as textual analysis, knowledge-based analysis, forecasting, data augmentation, planning, decision support, and simulations. Furthermore, the article provides a comprehensive collection of datasets, benchmarks, and useful code associated with mainstream applications, offering valuable resources for researchers and practitioners. The authors hope their work can help facilitate the adoption and further development of LLMs in finance and investment management.