# FinGPT: Open-Source Financial Large Language Models

**Authors:** Hongyang Yang, Xiao-Yang Liu, Christina Dan Wang  
**arXiv:** [2306.06031](https://arxiv.org/abs/2306.06031)  
**Date:** 2023-06-09  
**Summary page:** https://www.summarizepaper.com/en/paper/2306.06031v1/

## Key points

- Large language models (LLMs) have the potential to revolutionize natural language processing tasks in finance.
- Accessing high-quality financial data is the first challenge for financial LLMs (FinLLMs).
- FinGPT is an open-source large language model specifically designed for the finance sector.
- FinGPT takes a data-centric approach and provides accessible and transparent resources for researchers and practitioners to develop their FinLLMs.
- An automatic data curation pipeline and lightweight low-rank adaptation technique were used in building FinGPT.
- Potential applications of FinGPT include robo-advising, algorithmic trading, and low-code development.
- Collaborative efforts within the open-source AI4Finance community aim to democratize access to high-quality financial data and unlock new opportunities in open finance.
- Two associated code repositories are available on GitHub: \url{https://github.com/AI4Finance-Foundation/FinGPT} and \url{https://github.com/AI4Finance-Foundation/FinNLP}.
- The authors hope that by making FinGPT available as an open source resource, they can help accelerate progress towards more advanced FinLLMs.

## Summary

The potential of large language models (LLMs) to revolutionize natural language processing tasks in diverse domains has sparked great interest in finance. However, accessing high-quality financial data is the first challenge for financial LLMs (FinLLMs). To address this need, the authors present an open-source large language model called FinGPT for the finance sector. Unlike proprietary models, FinGPT takes a data-centric approach and provides researchers and practitioners with accessible and transparent resources to develop their FinLLMs. The authors highlight the importance of an automatic data curation pipeline and the lightweight low-rank adaptation technique in building FinGPT. Furthermore, they showcase several potential applications as stepping stones for users including robo-advising, algorithmic trading and low-code development. Through collaborative efforts within the open-source AI4Finance community, FinGPT aims to stimulate innovation by democratizing access to high-quality financial data and unlocking new opportunities in open finance. Two associated code repositories are available on GitHub: \url{https://github.com/AI4Finance-Foundation/FinGPT} and \url{https://github.com/AI4Finance-Foundation/FinNLP}. The authors hope that by making FinGPT available as an open source resource for researchers and practitioners in finance they can help accelerate progress towards more advanced FinLLMs.