FinGPT: Open-Source Financial Large Language Models (2023-06-09T00:00:00.000000Z)

TL;DR

This paper presents an open-source large language model, FinGPT, for the finance sector, and highlights the importance of an automatic data curation pipeline and the lightweight low-rank adaptation technique in building FinGPT.

Abstract

Large language models (LLMs) have shown the potential of revolutionizing natural language processing tasks in diverse domains, sparking great interest in finance. Accessing high-quality financial data is the first challenge for financial LLMs (FinLLMs). 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 develop their FinLLMs. We highlight the importance of an automatic data curation pipeline and the lightweight low-rank adaptation technique in building FinGPT. Furthermore, we showcase several potential applications as stepping stones for users, such as robo-advising, algorithmic trading, and low-code development. 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 https://github.com/AI4Finance-Foundation/FinGPT and https://github.com/AI4Finance-Foundation/FinNLP

Authors

Xiao-Yang Liu

4 papers

Hongyang Yang

4 papers

Chris Wang

3 papers

TL;DR

Abstract

Authors

References30 items

The Llama 3 Herd of Models

Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models

QLoRA: Efficient Finetuning of Quantized LLMs

BloombergGPT: A Large Language Model for Finance

FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning

When FLUE Meets FLANG: Benchmarks and Large Pretrained Language Model for Financial Domain

Training language models to follow instructions with human feedback

LaMDA: Language Models for Dialog Applications

FinRL: deep reinforcement learning framework to automate trading in quantitative finance

PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation

FinQA: A Dataset of Numerical Reasoning over Financial Data

LoRA: Low-Rank Adaptation of Large Language Models

Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art

Deep reinforcement learning for automated stock trading: an ensemble strategy

Language Models are Few-Shot Learners

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings

FinBERT: Financial Sentiment Analysis with Pre-trained Language Models

Attention is All you Need

How Twitter is Changing the Nature of Financial News Discovery

Et al

DeepSeek-V3 Technical Report

Fin-robot: An open-source ai agent platform for financial applications using large language models

Gemini: a family of highly capable multimodal models

Bernice: A Multilingual Pre-trained Encoder for Twitter

FinRead: A Transfer Learning Based Tool to Assess Readability of Definitions of Financial Terms

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Improving Language Understanding by Generative Pre-Training

Renard

Proceedings of the Second International Workshop on Data Science for Macro-Modeling

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names