Saved in:
Bibliographic Details
Main Authors: Ding, Tianyu, Banerjee, Adi, Mombaerts, Laurent, Li, Yunhong, Borogovac, Tarik, Weinstein, Juan Pablo De la Cruz
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.03759
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914939642314752
author Ding, Tianyu
Banerjee, Adi
Mombaerts, Laurent
Li, Yunhong
Borogovac, Tarik
Weinstein, Juan Pablo De la Cruz
author_facet Ding, Tianyu
Banerjee, Adi
Mombaerts, Laurent
Li, Yunhong
Borogovac, Tarik
Weinstein, Juan Pablo De la Cruz
contents The increasing use of Retrieval-Augmented Generation (RAG) systems in various applications necessitates stringent protocols to ensure RAG systems accuracy, safety, and alignment with user intentions. In this paper, we introduce VERA (Validation and Evaluation of Retrieval-Augmented Systems), a framework designed to enhance the transparency and reliability of outputs from large language models (LLMs) that utilize retrieved information. VERA improves the way we evaluate RAG systems in two important ways: (1) it introduces a cross-encoder based mechanism that encompasses a set of multidimensional metrics into a single comprehensive ranking score, addressing the challenge of prioritizing individual metrics, and (2) it employs Bootstrap statistics on LLM-based metrics across the document repository to establish confidence bounds, ensuring the repositorys topical coverage and improving the overall reliability of retrieval systems. Through several use cases, we demonstrate how VERA can strengthen decision-making processes and trust in AI applications. Our findings not only contribute to the theoretical understanding of LLM-based RAG evaluation metric but also promote the practical implementation of responsible AI systems, marking a significant advancement in the development of reliable and transparent generative AI technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03759
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VERA: Validation and Evaluation of Retrieval-Augmented Systems
Ding, Tianyu
Banerjee, Adi
Mombaerts, Laurent
Li, Yunhong
Borogovac, Tarik
Weinstein, Juan Pablo De la Cruz
Information Retrieval
Artificial Intelligence
I.2.7
The increasing use of Retrieval-Augmented Generation (RAG) systems in various applications necessitates stringent protocols to ensure RAG systems accuracy, safety, and alignment with user intentions. In this paper, we introduce VERA (Validation and Evaluation of Retrieval-Augmented Systems), a framework designed to enhance the transparency and reliability of outputs from large language models (LLMs) that utilize retrieved information. VERA improves the way we evaluate RAG systems in two important ways: (1) it introduces a cross-encoder based mechanism that encompasses a set of multidimensional metrics into a single comprehensive ranking score, addressing the challenge of prioritizing individual metrics, and (2) it employs Bootstrap statistics on LLM-based metrics across the document repository to establish confidence bounds, ensuring the repositorys topical coverage and improving the overall reliability of retrieval systems. Through several use cases, we demonstrate how VERA can strengthen decision-making processes and trust in AI applications. Our findings not only contribute to the theoretical understanding of LLM-based RAG evaluation metric but also promote the practical implementation of responsible AI systems, marking a significant advancement in the development of reliable and transparent generative AI technologies.
title VERA: Validation and Evaluation of Retrieval-Augmented Systems
topic Information Retrieval
Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2409.03759