用小模型高效转换金融合同，准确率媲美大模型。
Resource-Efficient LLM Application for Structured Transformation of Unstructured Financial Contracts
- 基于模板驱动方法确保转换格式正确
- 小开源模型在准确率上接近大模型
- 适合资源有限或注重隐私的金融机构
将非结构化法律合同转化为标准化、可机器读取的格式，对自动化金融流程至关重要。通用领域模型（CDM）为此提供了标准化框架，但将复杂法律文件如信用支持附件（CSAs）转化为CDM表示仍具挑战性。本文扩展了CDMizer框架——一种模板驱动的方法，在合同转CDM过程中保证语法正确性和符合CDM模式。我们将该框架应用于真实任务，与国际互换和衍生品协会（ISDA）为CSA条款提取开发的基准进行对比。结果显示，集成小型开源大语言模型（LLM）的CDMizer，在准确率和效率方面均达到与大型专有模型相当的水平。本工作凸显了资源高效解决方案在自动化法律合同转换中的潜力，提供了一种成本低、可扩展的方案，适用于资源受限或有严格数据隐私要求的金融机构。
原文摘要 · Abstract (English)
The transformation of unstructured legal contracts into standardized, machine-readable formats is essential for automating financial workflows. The Common Domain Model (CDM) provides a standardized framework for this purpose, but converting complex legal documents like Credit Support Annexes (CSAs) into CDM representations remains a significant challenge. In this paper, we present an extension of the CDMizer framework, a template-driven solution that ensures syntactic correctness and adherence to the CDM schema during contract-to-CDM conversion. We apply this extended framework to a real-world task, comparing its performance with a benchmark developed by the International Swaps and Derivatives Association (ISDA) for CSA clause extraction. Our results show that CDMizer, when integrated with a significantly smaller, open-source Large Language Model (LLM), achieves competitive performance in terms of accuracy and efficiency against larger, proprietary models. This work underscores the potential of resource-efficient solutions to automate legal contract transformation, offering a cost-effective and scalable approach that can meet the needs of financial institutions with constrained resources or strict data privacy requirements.
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。