_version_ 1866910992704733184
author Huang, Jimin
Xiao, Mengxi
Li, Dong
Jiang, Zihao
Yang, Yuzhe
Zhang, Yifei
Qian, Lingfei
Wang, Yan
Peng, Xueqing
Ren, Yang
Xiang, Ruoyu
Chen, Zhengyu
Zhang, Xiao
He, Yueru
Han, Weiguang
Chen, Shunian
Shen, Lihang
Kim, Daniel
Yu, Yangyang
Cao, Yupeng
Deng, Zhiyang
Li, Haohang
Feng, Duanyu
Dai, Yongfu
Somasundaram, VijayaSai
Lu, Peng
Xiong, Guojun
Liu, Zhiwei
Luo, Zheheng
Yao, Zhiyuan
Weng, Ruey-Ling
Qiu, Meikang
Smith, Kaleb E
Yu, Honghai
Lai, Yanzhao
Peng, Min
Nie, Jian-Yun
Suchow, Jordan W.
Liu, Xiao-Yang
Wang, Benyou
Lopez-Lira, Alejandro
Xie, Qianqian
Ananiadou, Sophia
Tsujii, Junichi
author_facet Huang, Jimin
Xiao, Mengxi
Li, Dong
Jiang, Zihao
Yang, Yuzhe
Zhang, Yifei
Qian, Lingfei
Wang, Yan
Peng, Xueqing
Ren, Yang
Xiang, Ruoyu
Chen, Zhengyu
Zhang, Xiao
He, Yueru
Han, Weiguang
Chen, Shunian
Shen, Lihang
Kim, Daniel
Yu, Yangyang
Cao, Yupeng
Deng, Zhiyang
Li, Haohang
Feng, Duanyu
Dai, Yongfu
Somasundaram, VijayaSai
Lu, Peng
Xiong, Guojun
Liu, Zhiwei
Luo, Zheheng
Yao, Zhiyuan
Weng, Ruey-Ling
Qiu, Meikang
Smith, Kaleb E
Yu, Honghai
Lai, Yanzhao
Peng, Min
Nie, Jian-Yun
Suchow, Jordan W.
Liu, Xiao-Yang
Wang, Benyou
Lopez-Lira, Alejandro
Xie, Qianqian
Ananiadou, Sophia
Tsujii, Junichi
contents Financial LLMs hold promise for advancing financial tasks and domain-specific applications. However, they are limited by scarce corpora, weak multimodal capabilities, and narrow evaluations, making them less suited for real-world application. To address this, we introduce \textit{Open-FinLLMs}, the first open-source multimodal financial LLMs designed to handle diverse tasks across text, tabular, time-series, and chart data, excelling in zero-shot, few-shot, and fine-tuning settings. The suite includes FinLLaMA, pre-trained on a comprehensive 52-billion-token corpus; FinLLaMA-Instruct, fine-tuned with 573K financial instructions; and FinLLaVA, enhanced with 1.43M multimodal tuning pairs for strong cross-modal reasoning. We comprehensively evaluate Open-FinLLMs across 14 financial tasks, 30 datasets, and 4 multimodal tasks in zero-shot, few-shot, and supervised fine-tuning settings, introducing two new multimodal evaluation datasets. Our results show that Open-FinLLMs outperforms afvanced financial and general LLMs such as GPT-4, across financial NLP, decision-making, and multi-modal tasks, highlighting their potential to tackle real-world challenges. To foster innovation and collaboration across academia and industry, we release all codes (https://anonymous.4open.science/r/PIXIU2-0D70/B1D7/LICENSE) and models under OSI-approved licenses.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11878
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
Huang, Jimin
Xiao, Mengxi
Li, Dong
Jiang, Zihao
Yang, Yuzhe
Zhang, Yifei
Qian, Lingfei
Wang, Yan
Peng, Xueqing
Ren, Yang
Xiang, Ruoyu
Chen, Zhengyu
Zhang, Xiao
He, Yueru
Han, Weiguang
Chen, Shunian
Shen, Lihang
Kim, Daniel
Yu, Yangyang
Cao, Yupeng
Deng, Zhiyang
Li, Haohang
Feng, Duanyu
Dai, Yongfu
Somasundaram, VijayaSai
Lu, Peng
Xiong, Guojun
Liu, Zhiwei
Luo, Zheheng
Yao, Zhiyuan
Weng, Ruey-Ling
Qiu, Meikang
Smith, Kaleb E
Yu, Honghai
Lai, Yanzhao
Peng, Min
Nie, Jian-Yun
Suchow, Jordan W.
Liu, Xiao-Yang
Wang, Benyou
Lopez-Lira, Alejandro
Xie, Qianqian
Ananiadou, Sophia
Tsujii, Junichi
Computation and Language
Computational Engineering, Finance, and Science
Computational Finance
Financial LLMs hold promise for advancing financial tasks and domain-specific applications. However, they are limited by scarce corpora, weak multimodal capabilities, and narrow evaluations, making them less suited for real-world application. To address this, we introduce \textit{Open-FinLLMs}, the first open-source multimodal financial LLMs designed to handle diverse tasks across text, tabular, time-series, and chart data, excelling in zero-shot, few-shot, and fine-tuning settings. The suite includes FinLLaMA, pre-trained on a comprehensive 52-billion-token corpus; FinLLaMA-Instruct, fine-tuned with 573K financial instructions; and FinLLaVA, enhanced with 1.43M multimodal tuning pairs for strong cross-modal reasoning. We comprehensively evaluate Open-FinLLMs across 14 financial tasks, 30 datasets, and 4 multimodal tasks in zero-shot, few-shot, and supervised fine-tuning settings, introducing two new multimodal evaluation datasets. Our results show that Open-FinLLMs outperforms afvanced financial and general LLMs such as GPT-4, across financial NLP, decision-making, and multi-modal tasks, highlighting their potential to tackle real-world challenges. To foster innovation and collaboration across academia and industry, we release all codes (https://anonymous.4open.science/r/PIXIU2-0D70/B1D7/LICENSE) and models under OSI-approved licenses.
title Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
topic Computation and Language
Computational Engineering, Finance, and Science
Computational Finance
url https://arxiv.org/abs/2408.11878