Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hu, Junyi, Zhou, You, Wang, Jie
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2410.02932
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913530430619648
author Hu, Junyi
Zhou, You
Wang, Jie
author_facet Hu, Junyi
Zhou, You
Wang, Jie
contents We introduce the Overall Performance Index (OPI), an intrinsic metric to evaluate retrieval-augmented generation (RAG) mechanisms for applications involving deep-logic queries. OPI is computed as the harmonic mean of two key metrics: the Logical-Relation Correctness Ratio and the average of BERT embedding similarity scores between ground-truth and generated answers. We apply OPI to assess the performance of LangChain, a popular RAG tool, using a logical relations classifier fine-tuned from GPT-4o on the RAG-Dataset-12000 from Hugging Face. Our findings show a strong correlation between BERT embedding similarity scores and extrinsic evaluation scores. Among the commonly used retrievers, the cosine similarity retriever using BERT-based embeddings outperforms others, while the Euclidean distance-based retriever exhibits the weakest performance. Furthermore, we demonstrate that combining multiple retrievers, either algorithmically or by merging retrieved sentences, yields superior performance compared to using any single retriever alone.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02932
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Intrinsic Evaluation of RAG Systems for Deep-Logic Questions
Hu, Junyi
Zhou, You
Wang, Jie
Artificial Intelligence
I.2.7
We introduce the Overall Performance Index (OPI), an intrinsic metric to evaluate retrieval-augmented generation (RAG) mechanisms for applications involving deep-logic queries. OPI is computed as the harmonic mean of two key metrics: the Logical-Relation Correctness Ratio and the average of BERT embedding similarity scores between ground-truth and generated answers. We apply OPI to assess the performance of LangChain, a popular RAG tool, using a logical relations classifier fine-tuned from GPT-4o on the RAG-Dataset-12000 from Hugging Face. Our findings show a strong correlation between BERT embedding similarity scores and extrinsic evaluation scores. Among the commonly used retrievers, the cosine similarity retriever using BERT-based embeddings outperforms others, while the Euclidean distance-based retriever exhibits the weakest performance. Furthermore, we demonstrate that combining multiple retrievers, either algorithmically or by merging retrieved sentences, yields superior performance compared to using any single retriever alone.
title Intrinsic Evaluation of RAG Systems for Deep-Logic Questions
topic Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2410.02932