Large language models can use attention scores as a natural indicator of the relevance and significance of retrieved external knowledge, as supported by Yang et al. (2024) and Ben-Artzy and Schwartz (2024).

Authors

• Person: Not available Organization: arXiv
  Empowering GraphRAG with Knowledge Filtering and Integration

Sources

• Empowering GraphRAG with Knowledge Filtering and Integration arxiv.org arXiv via serper

Referenced by nodes (2)

• Large Language Models concept
• external knowledge base concept