Titre du projet
Knowledge Base-Enhanced Prompting for Relationship Extraction
using Large Language Models
using Large Language Models
Nom de l'appel d'offre
International Mobility
Agence de moyen
Institut Convergence
Etat
Accepté
Année de soumission
2024
Equipe(s)
Bibliome
Coordinateur.trice
Claire Nédellec
Participants de MaIAGE
R. Bossy, C. Nédellec
Partenaires (hors MaIAGE)
Jingbo Xia
Année de démarrage - Année de fin de projet
2025
Date de fin du projet
Résumé
The diversity and highly structured nature of the information explicitly provided to the LLM significantly complicate the construction of hard prompts. Building on prior research in event extraction and knowledge injection for LLMs, we will explore various representation strategies. One direction involves comparing formal representations of relationship schemas (including argument types and relationship labels) and explicit Knowledge Base (KB) information, with their verbalized counterparts. Furthermore, the ordering of prompt components, whether by semantic similarity or intrinsic nature, has emerged as a critical factor and will be rigorously assessed.