← all papers · overview

Multi-meta-rag: Improving RAG For Multi-hop Queries Using Database Filtering With Llm-extracted Metadata

Abstract

The retrieval-augmented generation (RAG) enables retrieval of relevant information from an external knowledge source and allows large language models (LLMs) to answer queries over previously unseen document collections. However, it was demonstrated that traditional RAG applications perform poorly in answering multi-hop questions, which require retrieving and reasoning over multiple elements of sup

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).