arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.05151cs.CLcs.LG
收藏

探索大型语言模型在金融应用中的潜力:技术、性能与挑战——以FinMA为例

Exploring Large Language Models for Financial Applications: Techniques, Performance, and Challenges with FinMA

Lyman Briggs College, Michigan State University(密歇根州立大学Lyman Briggs学院);Department of Finance, Michigan State University(密歇根州立大学金融系);African Institute for Mathematical Sciences, Rwanda(刚果(金)数学科学研究所)

Prudence Djagba, Abdelkader Y. Saley

AI总结:

本研究评估了PIXIU框架下的FinMA模型在金融NLP任务中的表现,发现其在情感分析和分类上表现良好,但在数值推理、实体识别和摘要生成上存在挑战,旨在为金融LLM的设计与评估提供见解。

摘要:

本研究探讨了领域自适应大型语言模型(LLMs)在金融自然语言处理(NLP)中的优势与不足。分析聚焦于FinMA,这是一个在PIXIU框架内创建的模型,评估其在专业金融任务中的表现。鉴于金融应用对准确性、可靠性和领域适应性的关键要求,本研究考察了FinMA的模型架构、利用金融指令微调(FIT)数据集进行的指令微调过程,以及其在FLARE基准下的评估。研究结果表明,FinMA在情感分析和分类任务中表现良好,但在涉及数值推理、实体识别和摘要生成的任务中面临显著挑战。这项工作旨在增进对如何有效设计和评估金融大型语言模型以辅助金融相关决策过程的理解。

英文摘要:

This research explores the strengths and weaknesses of domain-adapted Large Language Models (LLMs) in the context of financial natural language processing (NLP). The analysis centers on FinMA, a model created within the PIXIU framework, which is evaluated for its performance in specialized financial tasks. Recognizing the critical demands of accuracy, reliability, and domain adaptation in financial applications, this study examines FinMA's model architecture, its instruction tuning process utilizing the Financial Instruction Tuning (FIT) dataset, and its evaluation under the FLARE benchmark. Findings indicate that FinMA performs well in sentiment analysis and classification, but faces notable challenges in tasks involving numerical reasoning, entity recognition, and summarization. This work aims to advance the understanding of how financial LLMs can be effectively designed and evaluated to assist in finance-related decision-making processes.

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。

↑