1. LLaMandement: Large Language Models for Summarization of French Legislative Proposals
- Author
-
Gesnouin, Joseph, Tannier, Yannis, Da Silva, Christophe Gomes, Tapory, Hatim, Brier, Camille, Simon, Hugo, Rozenberg, Raphael, Woehrel, Hermann, Yakaabi, Mehdi El, Binder, Thomas, Marie, Guillaume, Caron, Emilie, Nogueira, Mathile, Fontas, Thomas, Puydebois, Laure, Theophile, Marie, Morandi, Stephane, Petit, Mael, Creissac, David, Ennouchy, Pauline, Valetoux, Elise, Visade, Celine, Balloux, Severine, Cortes, Emmanuel, Devineau, Pierre-Etienne, Tan, Ulrich, Mac Namara, Esther, and Yang, Su
- Subjects
Computer Science - Computation and Language ,Computer Science - Artificial Intelligence - 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., Comment: 21 pages, 9 figures
- Published
- 2024