BriefContext, proposed by Zhang et al. (2024a), employs a preflight check to predict relevance ranking between a user query and retrieved documents, dividing the process into multiple chunks for RAG subtasks using a map-reduce strategy.

Authors

• Person: Not available Organization: arXiv
  Large Language Models Meet Knowledge Graphs for Question ...

Sources

• Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv via serper

Referenced by nodes (1)

• RAG concept