arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.02315cs.CLq-fin.GN
收藏

金融领域大语言模型(FinLLMs)综述

A Survey of Large Language Models in Finance (FinLLMs)

The University of Sydney(悉尼大学);NRS Technology(NRS科技公司);The University of Melbourne(墨尔本大学);Pohang University of Science and Technology (POSTECH)(浦项科技大学)

Jean Lee, Nicholas Stevens, Soyeon Caren Han, Minseok Song

AI总结:

本综述全面梳理金融大语言模型(FinLLMs)的发展历程、技术方法、性能评估及机遇挑战,对比相关技术与基准任务,提出前沿研究方向,并整理公开数据集与基准以支持金融AI研究。

摘要:

大语言模型(LLMs)已在各类自然语言处理(NLP)任务中展现出卓越能力,吸引了包括金融服务在内的多个领域的关注。尽管通用领域LLMs的研究已十分广泛,且其在金融领域潜力巨大,但金融大语言模型(FinLLM)的研究仍较为有限。本综述对FinLLMs进行了全面梳理,涵盖其发展历程、技术方法、性能表现以及机遇与挑战。首先,我们按时间顺序梳理了从通用领域预训练语言模型(PLMs)到当前FinLLMs的发展脉络,涉及GPT系列、部分开源LLMs以及金融语言模型。其次,我们对比了金融PLMs与FinLLMs采用的五类技术,包括训练方法、训练数据及微调方法。第三,我们总结了六项基准任务与数据集上的性能评估结果。此外,我们还提出了八项前沿金融NLP任务与数据集,用于开发更完善的FinLLMs。最后,我们探讨了FinLLMs面临的机遇与挑战,例如幻觉问题、隐私问题与效率问题。为支持金融领域的AI研究,我们在GitHub上整理了一组公开可用的数据集与评估基准。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑