ARAGOG: Advanced RAG Output Grading

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Eibich, Matouš, Nagpal, Shivay, Fred-Ojala, Alexander
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914737132929024
author Eibich, Matouš
Nagpal, Shivay
Fred-Ojala, Alexander
author_facet Eibich, Matouš
Nagpal, Shivay
Fred-Ojala, Alexander
contents Retrieval-Augmented Generation (RAG) is essential for integrating external knowledge into Large Language Model (LLM) outputs. While the literature on RAG is growing, it primarily focuses on systematic reviews and comparisons of new state-of-the-art (SoTA) techniques against their predecessors, with a gap in extensive experimental comparisons. This study begins to address this gap by assessing various RAG methods' impacts on retrieval precision and answer similarity. We found that Hypothetical Document Embedding (HyDE) and LLM reranking significantly enhance retrieval precision. However, Maximal Marginal Relevance (MMR) and Cohere rerank did not exhibit notable advantages over a baseline Naive RAG system, and Multi-query approaches underperformed. Sentence Window Retrieval emerged as the most effective for retrieval precision, despite its variable performance on answer similarity. The study confirms the potential of the Document Summary Index as a competent retrieval approach. All resources related to this research are publicly accessible for further investigation through our GitHub repository ARAGOG (https://github.com/predlico/ARAGOG). We welcome the community to further this exploratory study in RAG systems.
format Preprint
id arxiv_https___arxiv_org_abs_2404_01037
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ARAGOG: Advanced RAG Output Grading
Eibich, Matouš
Nagpal, Shivay
Fred-Ojala, Alexander
Computation and Language
Information Retrieval
I.2.7
Retrieval-Augmented Generation (RAG) is essential for integrating external knowledge into Large Language Model (LLM) outputs. While the literature on RAG is growing, it primarily focuses on systematic reviews and comparisons of new state-of-the-art (SoTA) techniques against their predecessors, with a gap in extensive experimental comparisons. This study begins to address this gap by assessing various RAG methods' impacts on retrieval precision and answer similarity. We found that Hypothetical Document Embedding (HyDE) and LLM reranking significantly enhance retrieval precision. However, Maximal Marginal Relevance (MMR) and Cohere rerank did not exhibit notable advantages over a baseline Naive RAG system, and Multi-query approaches underperformed. Sentence Window Retrieval emerged as the most effective for retrieval precision, despite its variable performance on answer similarity. The study confirms the potential of the Document Summary Index as a competent retrieval approach. All resources related to this research are publicly accessible for further investigation through our GitHub repository ARAGOG (https://github.com/predlico/ARAGOG). We welcome the community to further this exploratory study in RAG systems.
title ARAGOG: Advanced RAG Output Grading
topic Computation and Language
Information Retrieval
I.2.7
url https://arxiv.org/abs/2404.01037