Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models

About

Existing neural information retrieval (IR) models have often been studied in homogeneous and narrow settings, which has considerably limited insights into their out-of-distribution (OOD) generalization capabilities. To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval. We leverage a careful selection of 18 publicly available datasets from diverse text retrieval tasks and domains and evaluate 10 state-of-the-art retrieval systems including lexical, sparse, dense, late-interaction and re-ranking architectures on the BEIR benchmark. Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs. In contrast, dense and sparse-retrieval models are computationally more efficient but often underperform other approaches, highlighting the considerable room for improvement in their generalization capabilities. We hope this framework allows us to better evaluate and understand existing retrieval systems, and contributes to accelerating progress towards better robust and generalizable systems in the future. BEIR is publicly available at https://github.com/UKPLab/beir.

Nandan Thakur, Nils Reimers, Andreas R\"uckl\'e, Abhishek Srivastava, Iryna Gurevych• 2021

Related benchmarks

TaskDatasetResultRank
Information RetrievalBEIR (test)
TREC-COVID Score0.757
76
RerankingMS MARCO (dev)
MRR@100.243
71
Information RetrievalBEIR
TREC-COVID0.757
59
Zero-shot Information RetrievalBEIR
Trec-Covid NDCG@10 (Zero-shot)61.9
27
Scientific Document RetrievalCSFCube (test)
M@1016.99
26
Scientific Document RetrievalDORIS-MAE (test)
M@1011.52
26
Information RetrievalMS MARCO in-domain
NDCG@100.408
18
Information RetrievalMS Marco
NDCG@1040.8
15
Information RetrievalBEIR v1.0 (test)
ARCD Score97.8
10
Showing 9 of 9 rows

Other info

Code

Follow for update