LLaMandement: Large Language Models for Summarization of French Legislative Proposals

TL;DR

LLaMandement is a fine-tuned large language model developed by the French government to automatically generate neutral summaries of legislative proposals, improving efficiency in parliamentary processes.

Contribution

This paper introduces LLaMandement, a specialized LLM for summarizing French legislative proposals, with publicly released models and training data.

Findings

Outperforms manual processing in scalability

Provides neutral, accurate summaries of legislative proposals

Released models and data for community use

Abstract

This report introduces LLaMandement, a state-of-the-art Large Language Model, fine-tuned by the French government and designed to enhance the efficiency and efficacy of processing parliamentary sessions (including the production of bench memoranda and documents required for interministerial meetings) by generating neutral summaries of legislative proposals. Addressing the administrative challenges of manually processing a growing volume of legislative amendments, LLaMandement stands as a significant legal technological milestone, providing a solution that exceeds the scalability of traditional human efforts while matching the robustness of a specialized legal drafter. We release all our fine-tuned models and training data to the community.