Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata

Mykhailo Poliakov, Nadiya Shvai
6/19/2024
cs.CLcs.AIcs.DB

Official code: mxpoliakov/Multi-Meta-RAG (44 stars, MIT, last commit 2025-10-31).

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 supporting evidence. We introduce a new method called Multi-Meta-RAG, which uses database filtering with LLM-extracted metadata to improve the RAG selection of the relevant documents from various sources, relevant to the question. While database filtering is specific to a set of questions from a particular domain and format, we found out that Multi-Meta-RAG greatly improves the results on the MultiHop-RAG benchmark. The code is available at https://github.com/mxpoliakov/Multi-Meta-RAG.

View on arXivView PDF

Code Implementations(1)

mxpoliakov/Multi-Meta-RAGOfficial100%
MIT

A repository for Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata

442PythonJun 1, 202411 months agoMIT

Similar Papers

MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries

91% match1 repo4682024

Optimizing Multi-Hop Document Retrieval Through Intermediate Representations

87% match2025

Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation

86% match2025

Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs

85% match2025

Adapting Large Language Models for Multi-Domain Retrieval-Augmented-Generation

84% match2025

RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation

84% match1 repo12025

Cite this paper

@article{poliakov2024multimetarag,
  title  = {Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata},
  author = {Mykhailo Poliakov and Nadiya Shvai},
  year   = {2024},
  eprint = {2406.13213},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.13213v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.13213.svg)](https://codeofpaper.com/paper/2406.13213)

Discussion