金融领域大型语言模型(FinLLMs)概览

Jean Lee, Nicholas Stevens, Soyeon Caren Han, Minseok Song
{"title":"金融领域大型语言模型(FinLLMs)概览","authors":"Jean Lee, Nicholas Stevens, Soyeon Caren Han, Minseok Song","doi":"arxiv-2402.02315","DOIUrl":null,"url":null,"abstract":"Large Language Models (LLMs) have shown remarkable capabilities across a wide\nvariety of Natural Language Processing (NLP) tasks and have attracted attention\nfrom multiple domains, including financial services. Despite the extensive\nresearch into general-domain LLMs, and their immense potential in finance,\nFinancial LLM (FinLLM) research remains limited. This survey provides a\ncomprehensive overview of FinLLMs, including their history, techniques,\nperformance, and opportunities and challenges. Firstly, we present a\nchronological overview of general-domain Pre-trained Language Models (PLMs)\nthrough to current FinLLMs, including the GPT-series, selected open-source\nLLMs, and financial LMs. Secondly, we compare five techniques used across\nfinancial PLMs and FinLLMs, including training methods, training data, and\nfine-tuning methods. Thirdly, we summarize the performance evaluations of six\nbenchmark tasks and datasets. In addition, we provide eight advanced financial\nNLP tasks and datasets for developing more sophisticated FinLLMs. Finally, we\ndiscuss the opportunities and the challenges facing FinLLMs, such as\nhallucination, privacy, and efficiency. To support AI research in finance, we\ncompile a collection of accessible datasets and evaluation benchmarks on\nGitHub.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Survey of Large Language Models in Finance (FinLLMs)\",\"authors\":\"Jean Lee, Nicholas Stevens, Soyeon Caren Han, Minseok Song\",\"doi\":\"arxiv-2402.02315\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Large Language Models (LLMs) have shown remarkable capabilities across a wide\\nvariety of Natural Language Processing (NLP) tasks and have attracted attention\\nfrom multiple domains, including financial services. Despite the extensive\\nresearch into general-domain LLMs, and their immense potential in finance,\\nFinancial LLM (FinLLM) research remains limited. This survey provides a\\ncomprehensive overview of FinLLMs, including their history, techniques,\\nperformance, and opportunities and challenges. Firstly, we present a\\nchronological overview of general-domain Pre-trained Language Models (PLMs)\\nthrough to current FinLLMs, including the GPT-series, selected open-source\\nLLMs, and financial LMs. Secondly, we compare five techniques used across\\nfinancial PLMs and FinLLMs, including training methods, training data, and\\nfine-tuning methods. Thirdly, we summarize the performance evaluations of six\\nbenchmark tasks and datasets. In addition, we provide eight advanced financial\\nNLP tasks and datasets for developing more sophisticated FinLLMs. Finally, we\\ndiscuss the opportunities and the challenges facing FinLLMs, such as\\nhallucination, privacy, and efficiency. To support AI research in finance, we\\ncompile a collection of accessible datasets and evaluation benchmarks on\\nGitHub.\",\"PeriodicalId\":501372,\"journal\":{\"name\":\"arXiv - QuantFin - General Finance\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-02-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - General Finance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2402.02315\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - General Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2402.02315","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

大型语言模型(LLM)在各种自然语言处理(NLP)任务中表现出了非凡的能力,吸引了包括金融服务在内的多个领域的关注。尽管对通用领域 LLM 的研究十分广泛,而且它们在金融领域具有巨大潜力,但金融 LLM(FinLLM)的研究仍然有限。本调查全面概述了金融 LLM,包括其历史、技术、性能以及机遇和挑战。首先,我们对一般领域的预训练语言模型(PLM)到当前的金融 LLM(包括 GPT 系列、选定的开源 LLM 和金融 LM)进行了梳理。其次,我们比较了金融 PLM 和金融LLM 中使用的五种技术,包括训练方法、训练数据和微调方法。第三,我们总结了六个基准任务和数据集的性能评估。此外,我们还提供了八个高级金融 NLP 任务和数据集,用于开发更复杂的 FinLLM。最后,我们讨论了 FinLLMs 所面临的机遇和挑战,如识别、隐私和效率。为了支持金融领域的人工智能研究,我们在 GitHub 上编译了一系列可访问的数据集和评估基准。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A Survey of Large Language Models in Finance (FinLLMs)
Large Language Models (LLMs) have shown remarkable capabilities across a wide variety of Natural Language Processing (NLP) tasks and have attracted attention from multiple domains, including financial services. Despite the extensive research into general-domain LLMs, and their immense potential in finance, Financial LLM (FinLLM) research remains limited. This survey provides a comprehensive overview of FinLLMs, including their history, techniques, performance, and opportunities and challenges. Firstly, we present a chronological overview of general-domain Pre-trained Language Models (PLMs) through to current FinLLMs, including the GPT-series, selected open-source LLMs, and financial LMs. Secondly, we compare five techniques used across financial PLMs and FinLLMs, including training methods, training data, and fine-tuning methods. Thirdly, we summarize the performance evaluations of six benchmark tasks and datasets. In addition, we provide eight advanced financial NLP tasks and datasets for developing more sophisticated FinLLMs. Finally, we discuss the opportunities and the challenges facing FinLLMs, such as hallucination, privacy, and efficiency. To support AI research in finance, we compile a collection of accessible datasets and evaluation benchmarks on GitHub.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Information Asymmetry Index: The View of Market Analysts Market Failures of Carbon Trading Hydrogen Development in China and the EU: A Recommended Tian Ji's Horse Racing Strategy Applying the Nash Bargaining Solution for a Reasonable Royalty II Auction theory and demography
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1