Salvato in:
Dettagli Bibliografici
Autori principali: Es, Shahul, James, Jithin, Espinosa-Anke, Luis, Schockaert, Steven
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2309.15217
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918000021471232
author Es, Shahul
James, Jithin
Espinosa-Anke, Luis
Schockaert, Steven
author_facet Es, Shahul
James, Jithin
Espinosa-Anke, Luis
Schockaert, Steven
contents We introduce Ragas (Retrieval Augmented Generation Assessment), a framework for reference-free evaluation of Retrieval Augmented Generation (RAG) pipelines. RAG systems are composed of a retrieval and an LLM based generation module, and provide LLMs with knowledge from a reference textual database, which enables them to act as a natural language layer between a user and textual databases, reducing the risk of hallucinations. Evaluating RAG architectures is, however, challenging because there are several dimensions to consider: the ability of the retrieval system to identify relevant and focused context passages, the ability of the LLM to exploit such passages in a faithful way, or the quality of the generation itself. With Ragas, we put forward a suite of metrics which can be used to evaluate these different dimensions \textit{without having to rely on ground truth human annotations}. We posit that such a framework can crucially contribute to faster evaluation cycles of RAG architectures, which is especially important given the fast adoption of LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2309_15217
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Ragas: Automated Evaluation of Retrieval Augmented Generation
Es, Shahul
James, Jithin
Espinosa-Anke, Luis
Schockaert, Steven
Computation and Language
We introduce Ragas (Retrieval Augmented Generation Assessment), a framework for reference-free evaluation of Retrieval Augmented Generation (RAG) pipelines. RAG systems are composed of a retrieval and an LLM based generation module, and provide LLMs with knowledge from a reference textual database, which enables them to act as a natural language layer between a user and textual databases, reducing the risk of hallucinations. Evaluating RAG architectures is, however, challenging because there are several dimensions to consider: the ability of the retrieval system to identify relevant and focused context passages, the ability of the LLM to exploit such passages in a faithful way, or the quality of the generation itself. With Ragas, we put forward a suite of metrics which can be used to evaluate these different dimensions \textit{without having to rely on ground truth human annotations}. We posit that such a framework can crucially contribute to faster evaluation cycles of RAG architectures, which is especially important given the fast adoption of LLMs.
title Ragas: Automated Evaluation of Retrieval Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2309.15217