DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning

Wei Chen, Qiushi Wang, Zefei Long, Xianyin Zhang, Zhongtian Lu +6 more
10/23/2023
cs.CL

Official code: FudanDISC/DISC-FinLLM (885 stars, Apache-2.0, last commit 2023-11-01).

Abstract

We propose Multiple Experts Fine-tuning Framework to build a financial large language model (LLM), DISC-FinLLM. Our methodology improves general LLMs by endowing them with multi-turn question answering abilities, domain text processing capabilities, mathematical computation skills, and retrieval-enhanced generation capabilities. We build a financial instruction-tuning dataset named DISC-FIN-SFT, including instruction samples of four categories (consulting, NLP tasks, computing and retrieval-augmented generation). Evaluations conducted on multiple benchmarks demonstrate that our model performs better than baseline models in various financial scenarios. Further resources can be found at https://github.com/FudanDISC/DISC-FinLLM.

View on arXivView PDF

Code Implementations(1)

FudanDISC/DISC-FinLLMOfficial100%
Apache-2.0

DISC-FinLLM，中文金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financial consulting services in financial scenarios.

88594PythonOct 24, 20232 years agoApache-2.0
chain-of-retrievalfinancial-large-language-modelinstruction-tuningretrieval-enhanced-generationtool-learning

Similar Papers

PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance

92% match1 repo8862023

CFGPT: Chinese Financial Assistant with Large Language Model

90% match1 repo942023

Large Language Models in Finance: A Survey

89% match2023

SNFinLLM: Systematic and Nuanced Financial Domain Adaptation of Chinese Large Language Models

89% match2024

ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning

88% match1 repo72026

FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis

88% match1 repo252023

Cite this paper

@article{chen2023discfinllm,
  title  = {DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning},
  author = {Wei Chen and Qiushi Wang and Zefei Long and Xianyin Zhang and Zhongtian Lu and Bingxuan Li and Siyuan Wang and Jiarong Xu and Xiang Bai and Xuanjing Huang and Zhongyu Wei},
  year   = {2023},
  eprint = {2310.15205},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.15205v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.15205.svg)](https://codeofpaper.com/paper/2310.15205)

Discussion