English

Certifying One-Phase Technology-Assisted Reviews

Information Retrieval 2021-08-31 v1 Machine Learning

Abstract

Technology-assisted review (TAR) workflows based on iterative active learning are widely used in document review applications. Most stopping rules for one-phase TAR workflows lack valid statistical guarantees, which has discouraged their use in some legal contexts. Drawing on the theory of quantile estimation, we provide the first broadly applicable and statistically valid sample-based stopping rules for one-phase TAR. We further show theoretically and empirically that overshooting a recall target, which has been treated as innocuous or desirable in past evaluations of stopping rules, is a major source of excess cost in one-phase TAR workflows. Counterintuitively, incurring a larger sampling cost to reduce excess recall leads to lower total cost in almost all scenarios.

Keywords

Cite

@article{arxiv.2108.12746,
  title  = {Certifying One-Phase Technology-Assisted Reviews},
  author = {David D. Lewis and Eugene Yang and Ophir Frieder},
  journal= {arXiv preprint arXiv:2108.12746},
  year   = {2021}
}

Comments

10 pages, 4 figures, accepted at CIKM 2021

R2 v1 2026-06-24T05:29:54.643Z