English

A Generalised and Adaptable Reinforcement Learning Stopping Method

Information Retrieval 2025-07-08 v2

Abstract

This paper presents a Technology Assisted Review (TAR) stopping approach based on Reinforcement Learning (RL). Previous such approaches offered limited control over stopping behaviour, such as fixing the target recall and tradeoff between preferring to maximise recall or cost. These limitations are overcome by introducing a novel RL environment, GRLStop, that allows a single model to be applied to multiple target recalls, balances the recall/cost tradeoff and integrates a classifier. Experiments were carried out on six benchmark datasets (CLEF e-Health datasets 2017-9, TREC Total Recall, TREC Legal and Reuters RCV1) at multiple target recall levels. Results showed that the proposed approach to be effective compared to multiple baselines in addition to offering greater flexibility.

Keywords

Cite

@article{arxiv.2505.01907,
  title  = {A Generalised and Adaptable Reinforcement Learning Stopping Method},
  author = {Reem Bin-Hezam and Mark Stevenson},
  journal= {arXiv preprint arXiv:2505.01907},
  year   = {2025}
}

Comments

Accepted by SIGIR2025, Figure 4 legend updated

R2 v1 2026-06-28T23:20:17.697Z