Multi-Head RAG: Solving Multi-Aspect Problems with LLMs

Maciej Besta, Ales Kubicek, Robert Gerstenberger, Marcin Chrapek, Roman Niggli, Patrik Okanovic, Yi Zhu, Patrick Iff, Michal Podstawski, Lucas Weitzendorf, Mingyuan Chi, Joanna Gajda, Piotr Nyczyk, Jürgen Müller, Hubert Niewiadomski, Torsten Hoefler · Jun 7, 2024 · Citations: 0

Automatic Metrics Coding

Open arXiv RSS feed

Abstract

Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by retrieving supporting documents into the prompt, but existing methods do not explicitly target queries that require fetching multiple documents with substantially different content. Such multi-aspect queries are challenging because relevant documents can be far apart in embedding space, making joint retrieval difficult. We introduce Multi-Head RAG (MRAG), which addresses this gap with a simple yet powerful idea: using Transformer multi-head attention activations rather than the standard decoder-layer embedding, as retrieval keys. It leverages the observation that different heads capture different semantic aspects. This yields multi-aspect embeddings for both documents and queries, improving retrieval accuracy on complex queries. We show MRAG's design advantages over 18 RAG baselines, up to 20% higher retrieval success ratios for real-world use cases, and improved downstream LLM generation. MRAG integrates seamlessly with existing RAG frameworks and benchmarks.

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: Coding

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.45
Flags: low_signal, possible_false_positive

Research Summary

Contribution Summary

Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by retrieving supporting documents into the prompt, but existing methods do not explicitly target queries that require fetching multiple documents with substantially
Such multi-aspect queries are challenging because relevant documents can be far apart in embedding space, making joint retrieval difficult.
We introduce Multi-Head RAG (MRAG), which addresses this gap with a simple yet powerful idea: using Transformer multi-head attention activations rather than the standard decoder-layer embedding, as retrieval keys.

Why It Matters For Eval

MRAG integrates seamlessly with existing RAG frameworks and benchmarks.