RAGe: A Retrieval-Augmented Generation Evaluation Framework

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Guder, Larissa, de Moura, João Pedro, Accorsi, Arthur, Amaral, Gustavo Losch do, Magnaguagno, Maurício Cecílio, Meneguzzi, Felipe, Pinho, Marcio Sorraglia, Griebler, Dalvan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910261525348352
author Guder, Larissa
de Moura, João Pedro
Accorsi, Arthur
Amaral, Gustavo Losch do
Magnaguagno, Maurício Cecílio
Meneguzzi, Felipe
Pinho, Marcio Sorraglia
Griebler, Dalvan
author_facet Guder, Larissa
de Moura, João Pedro
Accorsi, Arthur
Amaral, Gustavo Losch do
Magnaguagno, Maurício Cecílio
Meneguzzi, Felipe
Pinho, Marcio Sorraglia
Griebler, Dalvan
contents Deploying Large Language Model (LLM) applications, particularly those relying on Retrieval-Augmented Generation (RAG), remains challenging due to high computational demands, outdated knowledge bases, and the need to manually select optimal pipeline components. In this work, we propose a modular framework for benchmarking and guiding the efficient development of RAG applications by focusing on resource telemetry and component recommendation, suggesting the best components for a domain-specific dataset. Our approach leverages core techniques in LLM applications, including document chunking, vector databases, embedding models, and retrievers, to evaluate trade-offs among accuracy, efficiency, and scalability. By directly correlating retrieval and generation quality with underlying hardware constraints, RAGe supports researchers to identify the most effective, domain-specific RAG setups for their specific operational needs, facilitating rapid prototyping even on consumer-grade hardware.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27445
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RAGe: A Retrieval-Augmented Generation Evaluation Framework
Guder, Larissa
de Moura, João Pedro
Accorsi, Arthur
Amaral, Gustavo Losch do
Magnaguagno, Maurício Cecílio
Meneguzzi, Felipe
Pinho, Marcio Sorraglia
Griebler, Dalvan
Information Retrieval
Artificial Intelligence
Deploying Large Language Model (LLM) applications, particularly those relying on Retrieval-Augmented Generation (RAG), remains challenging due to high computational demands, outdated knowledge bases, and the need to manually select optimal pipeline components. In this work, we propose a modular framework for benchmarking and guiding the efficient development of RAG applications by focusing on resource telemetry and component recommendation, suggesting the best components for a domain-specific dataset. Our approach leverages core techniques in LLM applications, including document chunking, vector databases, embedding models, and retrievers, to evaluate trade-offs among accuracy, efficiency, and scalability. By directly correlating retrieval and generation quality with underlying hardware constraints, RAGe supports researchers to identify the most effective, domain-specific RAG setups for their specific operational needs, facilitating rapid prototyping even on consumer-grade hardware.
title RAGe: A Retrieval-Augmented Generation Evaluation Framework
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2605.27445