AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Jianlyu, Wang, Nan, Li, Chaofan, Wang, Bo, Xiao, Shitao, Xiao, Han, Liao, Hao, Lian, Defu, Liu, Zheng
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915407096446976
author Chen, Jianlyu
Wang, Nan
Li, Chaofan
Wang, Bo
Xiao, Shitao
Xiao, Han
Liao, Hao
Lian, Defu
Liu, Zheng
author_facet Chen, Jianlyu
Wang, Nan
Li, Chaofan
Wang, Bo
Xiao, Shitao
Xiao, Han
Liao, Hao
Lian, Defu
Liu, Zheng
contents Evaluation plays a crucial role in the advancement of information retrieval (IR) models. However, current benchmarks, which are based on predefined domains and human-labeled data, face limitations in addressing evaluation needs for emerging domains both cost-effectively and efficiently. To address this challenge, we propose the Automated Heterogeneous Information Retrieval Benchmark (AIR-Bench). AIR-Bench is distinguished by three key features: 1) Automated. The testing data in AIR-Bench is automatically generated by large language models (LLMs) without human intervention. 2) Heterogeneous. The testing data in AIR-Bench is generated with respect to diverse tasks, domains and languages. 3) Dynamic. The domains and languages covered by AIR-Bench are constantly augmented to provide an increasingly comprehensive evaluation benchmark for community developers. We develop a reliable and robust data generation pipeline to automatically create diverse and high-quality evaluation datasets based on real-world corpora. Our findings demonstrate that the generated testing data in AIR-Bench aligns well with human-labeled testing data, making AIR-Bench a dependable benchmark for evaluating IR models. The resources in AIR-Bench are publicly available at https://github.com/AIR-Bench/AIR-Bench.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13102
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
Chen, Jianlyu
Wang, Nan
Li, Chaofan
Wang, Bo
Xiao, Shitao
Xiao, Han
Liao, Hao
Lian, Defu
Liu, Zheng
Information Retrieval
Computation and Language
Evaluation plays a crucial role in the advancement of information retrieval (IR) models. However, current benchmarks, which are based on predefined domains and human-labeled data, face limitations in addressing evaluation needs for emerging domains both cost-effectively and efficiently. To address this challenge, we propose the Automated Heterogeneous Information Retrieval Benchmark (AIR-Bench). AIR-Bench is distinguished by three key features: 1) Automated. The testing data in AIR-Bench is automatically generated by large language models (LLMs) without human intervention. 2) Heterogeneous. The testing data in AIR-Bench is generated with respect to diverse tasks, domains and languages. 3) Dynamic. The domains and languages covered by AIR-Bench are constantly augmented to provide an increasingly comprehensive evaluation benchmark for community developers. We develop a reliable and robust data generation pipeline to automatically create diverse and high-quality evaluation datasets based on real-world corpora. Our findings demonstrate that the generated testing data in AIR-Bench aligns well with human-labeled testing data, making AIR-Bench a dependable benchmark for evaluating IR models. The resources in AIR-Bench are publicly available at https://github.com/AIR-Bench/AIR-Bench.
title AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2412.13102