Communication Dans Un Congrès Année : 2025

GraphRAG: Leveraging Graph-Based Efficiency to Minimize Hallucinations in LLM-Driven RAG for Finance Data

Gaëtan Caillaut
  • Fonction : Auteur
Pierre Halftermeyer
  • Fonction : Auteur
  • PersonId : 963479
Raheel Qader
  • Fonction : Auteur
  • PersonId : 778121
  • IdRef : 224293559
Mehdi Mouayad
  • Fonction : Auteur
  • PersonId : 1495557
Fabrice Le Deit
  • Fonction : Auteur
Joseph Gesnouin

Résumé

This study explores the integration of graphbased methods into Retrieval-Augmented Generation (RAG) systems to enhance efficiency, reduce hallucinations, and improve explainability, with a particular focus on financial and regulatory document retrieval. We propose two strategies-FactRAG and HybridRAG-which leverage knowledge graphs to improve RAG performance. Experiments conducted using Finance Bench, a benchmark for AI in finance, demonstrate that these approaches achieve a 6% reduction in hallucinations and an 80% decrease in token usage compared to conventional RAG methods. Furthermore, we evaluate HybridRAG by comparing the Digital Operational Resilience Act (DORA) from the European Union with the Federal Financial Institutions Examination Council (FFIEC) guidelines from the United States. The results reveal a significant improvement in computational efficiency, reducing contradiction detection complexity from O(n 2 ) to O(k •n)-where n is the number of chunks-and a remarkable 734-fold decrease in token consumption. Graph-based retrieval methods can improve the efficiency and cost-effectiveness of large language model (LLM) applications, though their performance and token usage depend on the dataset, knowledge graph design, and retrieval task.
Fichier principal
Vignette du fichier
GraphRAG_CReady_SUBMITED_COLING25_KGraph_GenAI_Workshop.pdf (751.04 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04907346 , version 1 (22-01-2025)

Licence

Identifiants

  • HAL Id : hal-04907346 , version 1

Citer

Mariam Barry, Gaëtan Caillaut, Pierre Halftermeyer, Raheel Qader, Mehdi Mouayad, et al.. GraphRAG: Leveraging Graph-Based Efficiency to Minimize Hallucinations in LLM-Driven RAG for Finance Data. 31st International conference on Computational Linguistics Workshop Knowledge Graph & GenAI, Jan 2025, Abu Dhabi, United Arab Emirates. ⟨hal-04907346⟩
0 Consultations
0 Téléchargements

Partager

More