English

A Two-Stage Architecture for NDA Analysis: LLM-based Segmentation and Transformer-based Clause Classification

Computation and Language 2026-03-12 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2603.09990,
  title  = {A Two-Stage Architecture for NDA Analysis: LLM-based Segmentation and Transformer-based Clause Classification},
  author = {Ana Begnini and Matheus Vicente and Leonardo Souza},
  journal= {arXiv preprint arXiv:2603.09990},
  year   = {2026}
}

Comments

14 pages, 2 figures, 3 tables. Published at STIL @ BRACIS 2025

R2 v1 2026-07-01T11:13:30.293Z