用19个金融数据集测试了LoRA微调效果，平均性能提升36%。
FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets
- 在150份美国证监会文件上构建4个新数据集，覆盖财务分析场景
- 五种LoRA方法平均比基线模型准确率提升36%，推理时显存更低
- 开源代码与适配器，适合想低成本部署金融AI的研究者
低秩适应（LoRA）方法在将通用大语言模型扩展至数百甚至数千应用场景方面展现出巨大潜力。然而，其在高风险领域如金融中的有效性却很少被探索，例如通过CFA考试或分析美国证券交易委员会（SEC）文件。本文提出开源的FinLoRA项目，首次在通用和高度专业的金融任务上对多种LoRA方法进行基准测试。我们共收集19个涵盖多样化金融应用的数据集，特别基于150份SEC文件创建了4个全新的XBRL分析数据集。评估了5种LoRA方法与5个基础大型语言模型，并在准确率、F1值和BERTScore上报告结果，同时记录微调与推理阶段的时间与GPU显存消耗。实验表明，LoRA方法相较基线模型平均提升36%的性能。FinLoRA提供了一种经济且可扩展的路径，使金融智能普惠大众。所有数据集、LoRA适配器、代码与文档均公开于https://github.com/Open-Finance-Lab/FinLoRA。
原文摘要 · Abstract (English)
Low-rank adaptation (LoRA) methods show great potential for scaling pre-trained general-purpose Large Language Models (LLMs) to hundreds or thousands of use scenarios. However, their efficacy in high-stakes domains like finance is rarely explored, e.g., passing CFA exams and analyzing SEC filings. In this paper, we present the open-source FinLoRA project that benchmarks LoRA methods on both general and highly professional financial tasks. First, we curated 19 datasets covering diverse financial applications; in particular, we created four novel XBRL analysis datasets based on 150 SEC filings. Second, we evaluated five LoRA methods and five base LLMs. Finally, we provide extensive experimental results in terms of accuracy, F1, and BERTScore and report computational cost in terms of time and GPU memory during fine-tuning and inference stages. We find that LoRA methods achieved substantial performance gains of 36\% on average over base models. Our FinLoRA project provides an affordable and scalable approach to democratize financial intelligence to the general public. Datasets, LoRA adapters, code, and documentation are available at https://github.com/Open-Finance-Lab/FinLoRA
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。