用大模型自动拆分和分类商业保密协议条款，效率远超人工。
A Two-Stage Architecture for NDA Analysis: LLM-based Segmentation and Transformer-based Clause Classification
- 先用大语言模型拆分合同段落，再用微调的法律BERT分类条款类型。
- 段落分割的准确率高达95%，条款分类加权F1达85%。
- 适合法务自动化、合同智能处理等场景，尤其适合批量处理复杂合同。
在企业间合作中，签署保密协议（NDAs）十分常见。然而，这些文件在格式、结构和写作风格上差异巨大，导致人工分析耗时且易出错。本文提出一种两阶段架构，利用大语言模型实现合同段落自动分割与条款分类。第一阶段采用LLaMA-3.1-8B-Instruct模型进行条款提取，第二阶段使用微调的Legal-Roberta-Large模型完成分类。在分割任务中，取得0.95 ± 0.0036的ROUGE F1得分；在分类任务中，加权F1达到0.85，验证了该方法的可行性与高精度。
原文摘要 · Abstract (English)
In business-to-business relations, it is common to establish NonDisclosure Agreements (NDAs). However, these documents exhibit significant variation in format, structure, and writing style, making manual analysis slow and error-prone. We propose an architecture based on LLMs to automate the segmentation and clauses classification within these contracts. We employed two models: LLaMA-3.1-8B-Instruct for NDA segmentation (clause extraction) and a fine-tuned Legal-Roberta-Large for clause classification. In the segmentation task, we achieved a ROUGE F1 of 0.95 +/- 0.0036; for classification, we obtained a weighted F1 of 0.85, demonstrating the feasibility and precision of the approach.
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。