Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking

TL;DR

This paper advocates for more comprehensive IR benchmarking that includes efficiency metrics like latency and hardware costs alongside accuracy, to better reflect real-world deployment considerations.

Contribution

It introduces a framework for IR benchmarks to incorporate efficiency metrics, highlighting their impact on system choice and encouraging more holistic evaluation methods.

Findings

Efficiency considerations significantly influence IR system selection.

Current benchmarks focus mainly on accuracy, neglecting deployment costs.

Including efficiency metrics leads to different optimal IR system choices.

Abstract

Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks. Unfortunately, some dimensions of this progress are illusory: the majority of the popular IR benchmarks today focus exclusively on downstream task accuracy and thus conceal the costs incurred by systems that trade away efficiency for quality. Latency, hardware cost, and other efficiency considerations are paramount to the deployment of IR systems in user-facing settings. We propose that IR benchmarks structure their evaluation methodology to include not only metrics of accuracy, but also efficiency considerations such as a query latency and the corresponding cost budget for a reproducible hardware setting. For the popular IR benchmarks MS MARCO and XOR-TyDi, we show how the best choice of IR system varies according to how these efficiency considerations are chosen and weighed. We hope that future benchmarks will adopt these guidelines toward more holistic IR evaluation.