FinLLM at IJCAI 2023
8 PagesPosted: 3 Jul 2023
See all articles by Hongyang Yang
Hongyang Yang
AI4Finance Foundation
Xiao-Yang Liu
Columbia University - Fu Foundation School of Engineering and Applied Science
Christina Dan Wang
New York University (NYU) - New York University (NYU), Shanghai
Date Written: June 9, 2023
Abstract
Large language models (LLMs) have shown the potential of revolutionizing natural language processing in diverse domains, sparking great interest in finance. However, the finance domain presents unique challenges, including high temporal sensitivity, constant dynamism, and a low signal-to-noise ratio (SNR). While proprietary models like BloombergGPT have taken advantage of their unique data accumulation, such privileged access calls for an open-source alternative to democratize internet-scale financial data.
In this paper, we present an open-source large language model, FinGPT, for the finance sector. Unlike proprietary models, FinGPT takes a data-centric approach, providing researchers and practitioners with accessible and transparent resources to customize their financial LLMs (FinLLMs). We highlight the importance of an automatic data curation pipeline and the lightweight low-rank adaptation technique in building FinGPT. Furthermore, we will showcase potential applications as stepping stones for users, such as robo-advising and sentiment analysis. Through collaborative efforts within the open-source AI4Finance community, FinGPT aims to stimulate innovation, democratize FinLLMs, and unlock new opportunities in open finance. Two associated code repos are \url{https://github.com/AI4Finance-Foundation/FinGPT} and \url{https://github.com/AI4Finance-Foundation/FinNLP}
Keywords: large language model, FinGPT, open-source, democratization, data-centric
Suggested Citation:Suggested Citation
Yang, Hongyang and Liu, Xiao-Yang and Dan Wang, Christina, FinGPT: Open-Source Financial Large Language Models (June 9, 2023). FinLLM at IJCAI 2023, Available at SSRN: https://ssrn.com/abstract=4489826 or http://dx.doi.org/10.2139/ssrn.4489826
Hongyang Yang
AI4Finance Foundation ( email )
New York
New York, NY 10027
United States
Xiao-Yang Liu (Contact Author)
Columbia University - Fu Foundation School of Engineering and Applied Science ( email )
New York, NY
United States