IRSC: A Zero-shot Evaluation Benchmark for Information Retrieval through Semantic Comprehension in Retrieval-Augmented Generation Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Hai, Zhan, Shaoxiong, Su, Junyou, Zheng, Haitao, Wang, Hui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916411539980288
author Lin, Hai
Zhan, Shaoxiong
Su, Junyou
Zheng, Haitao
Wang, Hui
author_facet Lin, Hai
Zhan, Shaoxiong
Su, Junyou
Zheng, Haitao
Wang, Hui
contents In Retrieval-Augmented Generation (RAG) tasks using Large Language Models (LLMs), the quality of retrieved information is critical to the final output. This paper introduces the IRSC benchmark for evaluating the performance of embedding models in multilingual RAG tasks. The benchmark encompasses five retrieval tasks: query retrieval, title retrieval, part-of-paragraph retrieval, keyword retrieval, and summary retrieval. Our research addresses the current lack of comprehensive testing and effective comparison methods for embedding models in RAG scenarios. We introduced new metrics: the Similarity of Semantic Comprehension Index (SSCI) and the Retrieval Capability Contest Index (RCCI), and evaluated models such as Snowflake-Arctic, BGE, GTE, and M3E. Our contributions include: 1) the IRSC benchmark, 2) the SSCI and RCCI metrics, and 3) insights into the cross-lingual limitations of embedding models. The IRSC benchmark aims to enhance the understanding and development of accurate retrieval systems in RAG tasks. All code and datasets are available at: https://github.com/Jasaxion/IRSC_Benchmark
format Preprint
id arxiv_https___arxiv_org_abs_2409_15763
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle IRSC: A Zero-shot Evaluation Benchmark for Information Retrieval through Semantic Comprehension in Retrieval-Augmented Generation Scenarios
Lin, Hai
Zhan, Shaoxiong
Su, Junyou
Zheng, Haitao
Wang, Hui
Information Retrieval
Artificial Intelligence
In Retrieval-Augmented Generation (RAG) tasks using Large Language Models (LLMs), the quality of retrieved information is critical to the final output. This paper introduces the IRSC benchmark for evaluating the performance of embedding models in multilingual RAG tasks. The benchmark encompasses five retrieval tasks: query retrieval, title retrieval, part-of-paragraph retrieval, keyword retrieval, and summary retrieval. Our research addresses the current lack of comprehensive testing and effective comparison methods for embedding models in RAG scenarios. We introduced new metrics: the Similarity of Semantic Comprehension Index (SSCI) and the Retrieval Capability Contest Index (RCCI), and evaluated models such as Snowflake-Arctic, BGE, GTE, and M3E. Our contributions include: 1) the IRSC benchmark, 2) the SSCI and RCCI metrics, and 3) insights into the cross-lingual limitations of embedding models. The IRSC benchmark aims to enhance the understanding and development of accurate retrieval systems in RAG tasks. All code and datasets are available at: https://github.com/Jasaxion/IRSC_Benchmark
title IRSC: A Zero-shot Evaluation Benchmark for Information Retrieval through Semantic Comprehension in Retrieval-Augmented Generation Scenarios
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2409.15763