Legal Documents Drafting with Fine-Tuned Pre-Trained Large Language Model

TL;DR

This paper demonstrates that fine-tuning pre-trained large language models on annotation-free legal documents enables effective legal document drafting while preserving privacy and security, even on local computers.

Contribution

It introduces a method to fine-tune large language models on unlabeled legal texts without segmentation, addressing data scarcity and privacy concerns.

Findings

Effective legal draft generation without manual annotations

Fine-tuning on local computers enhances privacy and security

Achieves comparable performance to traditional supervised methods

Abstract

With the development of large-scale Language Models (LLM), fine-tuning pre-trained LLM has become a mainstream paradigm for solving downstream tasks of natural language processing. However, training a language model in the legal field requires a large number of legal documents so that the language model can learn legal terminology and the particularity of the format of legal documents. The typical NLP approaches usually rely on many manually annotated data sets for training. However, in the legal field application, it is difficult to obtain a large number of manually annotated data sets, which restricts the typical method applied to the task of drafting legal documents. The experimental results of this paper show that not only can we leverage a large number of annotation-free legal documents without Chinese word segmentation to fine-tune a large-scale language model, but more importantly, it can fine-tune a pre-trained LLM on the local computer to achieve the generating legal document drafts task, and at the same time achieve the protection of information privacy and to improve information security issues.