skip to main content
10.1145/3677052.3698637acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicaifConference Proceedingsconference-collections
research-article

Customized FinGPT Search Agents Using Foundation Models

Published: 14 November 2024 Publication History

Abstract

Current large language models (LLMs) have proven useful for analyzing financial data, but most existing models, such as BloombergGPT and FinGPT, lack customization for specific user needs. In this paper, we address this gap by developing FinGPT Search Agents tailored for two types of users: individuals and institutions. For individuals, we leverage Retrieval-Augmented Generation (RAG) to search local documents and user-specified data sources. For institutions, we employ dynamic vector databases and fine-tune models on proprietary data. There are several key issues to address, including data privacy, the time-sensitive nature of financial information, and the need for fast responses. Experiments show that FinGPT Search Agent outperform existing models in accuracy, relevance, and response time, making them promising for real-world financial applications.

References

[1]
Jina AI. 2024. Jina AI Reader. https://github.com/jina-ai/reader.
[2]
AI@Meta. 2024. Llama 3 Model Card. (2024). https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md
[3]
Ajay Byadgi. 2024. FinGPT-Individual-Agent-Performance. GitHub repository. https://github.com/AjayByadgi/FinGPT-Individual-Agent-Performance
[4]
Luiz Bonifacio, Hugo Abonizio, Marzieh Fadaee, and Rodrigo Nogueira. 2022. InPars: Data Augmentation for Information Retrieval using Large Language Models. arxiv:2202.05144 [cs.CL] https://arxiv.org/pdf/2202.05144
[5]
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems 33 (2020), 1877–1901.
[6]
Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, Nikolaos Aletras, and Ion Androutsopoulos. 2020. LEGAL-BERT: The Muppets straight out of Law School. EMNLP (2020).
[7]
Shuohang Chen, Weijia Qi, Xufang Mou, Yuhui Bai, Dawei Wang, Cheng Guo, Huayi Zhang, Chenguang Zhang, Lu Li, Yuxiao Yang, Jianfeng Ma, Ming-Wei Li, Minlie Huang, Jing Gao, and Yong Qi. 2023. MIND2WEB: Towards a Generalist Agent for the Web. In Advances in Neural Information Processing Systems (NeurIPS) 2023. https://proceedings.neurips.cc/paper_files/paper/2023/hash/5950bf290a1570ea401bf98882128160-Abstract-Datasets_and_Benchmarks.html
[8]
Google Colaboratory. 2024. Fetching and Parsing Local Files.
[9]
Tim Dettmers, Menashe Zeno, Jamie Hall, Punit Singh, Qiaozi Yang, Shubho Goel, Sayna Chandra, Omar Khalid, Mike Lewis, Rashid Mehmood, 2024. QLoRA: Efficient Finetuning of Quantized LLMs. Advances in Neural Information Processing Systems (2024).
[10]
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT.
[11]
Andre Esteva, Alexandre Robicquet, Bharath Ramsundar, Volodymyr Kuleshov, Mark DePristo, Kelvin Chou, Claire Cui, Greg Corrado, Jeff Dean, and Lucy Colwell. 2021. A guide to deep learning in healthcare. Nature Medicine 27, 1 (2021), 15–25.
[12]
Shijie Han, Haoqiang Kang, Bo Jin, Xiao-Yang Liu, and Steve Yang. 2024. XBRL Agent: Leveraging Large Language Models for Financial Report Analysis. In ACM International Conference on AI in Finance.
[13]
Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, and Dong Yu. 2024. WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models. arXiv preprint arXiv:2401.13919 (2024). https://arxiv.org/abs/2401.13919
[14]
Ronny Hoesada. 2023. Enhancing LLM Accuracy Using MongoDB Vector Search and Unstructured.io Metadata. https://www.mongodb.com/developer/products/atlas/llm-accuracy-vector-search-unstructured-metadata/.
[15]
Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen. 2023. LoRA: Low-rank adaptation of large language models. International Conference on Learning Representations (2023).
[16]
Pranab Islam, Anand Kannappan, Douwe Kiela, Rebecca Qian, Nino Scherrer, and Bertie Vidgen. 2023. FinanceBench: A New Benchmark for Financial Question Answering. arXiv preprint arXiv:2311.11944 (2023).
[17]
Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023). https://arxiv.org/abs/2310.06825
[18]
FINOS Labs. 2024. EMIR-Specific RAG Dataset. https://github.com/finos-labs/emir-specific-rag/tree/main. Accessed: 2024-07-30.
[19]
Xiao-Yang Liu, Guoxuan Wang, Hongyang Yang, and Daochen Zha. 2023. Data-Centric FinGPT: Democratizing Internet-scale Data for Financial Large Language Models. In Workshop on Instruction Tuning and Instruction Following, NeurIPS.
[20]
Xiao-Yang Liu, Ziyi Xia, Hongyang Yang, Jiechao Gao, Daochen Zha, Ming Zhu, Christina Dan Wang, Zhaoran Wang, and Jian Guo. 2024. Dynamic datasets and market environments for financial reinforcement learning. Machine Learning 113, 5 (2024), 2795–2839.
[21]
Xiao-Yang Liu, Jie Zhang, Guoxuan Wang, Weiqing Tong, and Anwar Walid. 2024. FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computing. arXiv preprint arXiv:2402.13533 (2024).
[22]
Xiao-Yang Liu, Yimeng Zhang, Yukang Liao, and Ling Jiang. 2023. Dynamic updating of the knowledge base for a large-scale question answering system. TALLIP 19, 3 (2023), 1–13.
[23]
Xiao-Yang Liu, Rongyi Zhu, Daochen Zha, Jiechao Gao, Shan Zhong, and Meikang Qiu. 2023. Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning. arXiv preprint arXiv:2312.17493 (2023). https://arxiv.org/abs/2312.17493
[24]
Youyang Ng, Daisuke Miyashita, Yasuto Hoshi, Yasuhiro Morioka, Osamu Torii, Tomoya Kodama, and Jun Deguchi. 2023. SimplyRetrieve: A Private and Lightweight Retrieval-Centric Generative AI Tool. arxiv:2308.03983 [cs.CL] https://arxiv.org/pdf/2308.03983
[25]
Yuqi Nie, Yaxuan Kong, Xiaowen Dong, John M Mulvey, H Vincent Poor, Qingsong Wen, and Stefan Zohren. 2024. A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges. arXiv preprint arXiv:2406.11903 (2024). https://arxiv.org/abs/2406.11903
[26]
OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023). https://arxiv.org/abs/2303.08774
[27]
OpenAI. 2024. Hello GPT-4o. https://openai.com/index/hello-gpt-4o/
[28]
Andrew Pen, Michael Wu, John Allard, Logan Kilpatrick, and Steven Heidel. 2023. GPT-3.5 Turbo fine-tuning and API updates. https://openai.com/index/gpt-3-5-turbo-fine-tuning-and-api-updates Accessed: 2024-08-02.
[29]
Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever, 2018. Improving language understanding by generative pre-training. (2018).
[30]
Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, 2023. LLaMA: Open and efficient foundation language models. arXiv preprint (2023). arXiv:arXiv:2302.13971
[31]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017), 30.
[32]
Shan Wu 2023. BloombergGPT: A large language model for finance. arXiv preprint arXiv:2304.15384 (2023).
[33]
Qianqian Xie, Weiguang Han, Zhengyu Chen, Ruoyu Xiang, Xiao Zhang, Yueru He, Mengxi Xiao, Dong Li, Yongfu Dai, Duanyu Feng, Yijing Xu, Haoqiang Kang, Ziyan Kuang, Chenhan Yuan, Kailai Yang, Zheheng Luo, Tianlin Zhang, Zhiwei Liu, Guojun Xiong, Zhiyang Deng, Yuechen Jiang, Zhiyuan Yao, Haohang Li, Yangyang Yu, Gang Hu, Jiajia Huang, Xiao-Yang Liu, Alejandro Lopez-Lira, Benyou Wang, Yanzhao Lai, Hao Wang, Min Peng, Sophia Ananiadou, and Jimin Huang. 2024. FinBen: A Holistic Financial Benchmark for Large Language Models. NeurIPS, Special Track on Datasets and Benchmarks (2024).
[34]
Qianqian Xie, Dong Li, Mengxi Xiao, Zihao Jiang, Ruoyu Xiang, Xiao Zhang, Zhengyu Chen, Yueru He, Weiguang Han, Yuzhe Yang, 2024. Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications. arXiv preprint arXiv:2408.11878 (2024). https://arxiv.org/abs/2408.11878
[35]
Hongyang Yang, Xiao-Yang Liu, and Christina Dan Wang. 2023. FinGPT: Open-Source Financial Large Language Models. FinLLM at IJCAI (2023).
[36]
Boyu Zhang, Hongyang Yang, Tianyu Zhou, Muhammad Ali Babar, and Xiao-Yang Liu. 2023. Enhancing financial sentiment analysis via retrieval augmented large language models. In Proceedings of the fourth ACM international conference on AI in finance. 349–356.
[37]
P Zhao, H Zhang, Q Yu, Z Wang, Y Geng, and F Fu. 2024. Retrieval-augmented generation for AI-generated content: A survey. arXiv preprint arXiv:2402.19473 (2024).
[38]
Yutao Zhu, Huaying Yuan, Shuting Wang, Jiongnan Liu, Wenhan Liu, Chenlong Deng, Haonan Chen, Zheng Liu, Zhicheng Dou, and Ji-Rong Wen. 2023. Large Language Models for Information Retrieval: A Survey. arXiv preprint arXiv:2308.07107 (2023). https://arxiv.org/abs/2308.07107

Index Terms

  1. Customized FinGPT Search Agents Using Foundation Models

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICAIF '24: Proceedings of the 5th ACM International Conference on AI in Finance
    November 2024
    878 pages
    ISBN:9798400710810
    DOI:10.1145/3677052
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 14 November 2024

    Permissions

    Request permissions for this article.

    Check for updates

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICAIF '24

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 157
      Total Downloads
    • Downloads (Last 12 months)157
    • Downloads (Last 6 weeks)39
    Reflects downloads up to 17 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media