# Efficient Test Collection Construction via Active Learning

arXiv: https://arxiv.org/abs/1801.05605 · HTML: https://mlsanity.com/paper/1801.05605/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2018.

## Built on by (most cited first, 7 of 7)

- [Mandoline: Model Evaluation under Distribution Shift](https://mlsanity.com/paper/2107.00643/) (2021)
- [On the Evaluation of Machine-Generated Reports](https://mlsanity.com/paper/2405.00982/) (2024)
- [An Information Retrieval Approach to Building Datasets for Hate Speech Detection](https://mlsanity.com/paper/2106.09775/) (2021)
- [Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories](https://mlsanity.com/paper/2109.05720/) (2021)
- [Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective](https://mlsanity.com/paper/2205.04105/) (2022)
- [Query Decomposition for RAG: Balancing Exploration-Exploitation](https://mlsanity.com/paper/2510.18633/) (2025)
- [Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation](https://mlsanity.com/paper/2604.20763/) (2026)

## Abstract (arXiv)

To create a new IR test collection at low cost, it is valuable to carefully select which documents merit human relevance judgments. Shared task campaigns such as NIST TREC pool document rankings from many participating systems (and often interactive runs as well) in order to identify the most likely relevant documents for human judging. However, if one's primary goal is merely to build a test collection, it would be useful to be able to do so without needing to run an entire shared task. Toward this end, we investigate multiple active learning strategies which, without reliance on system rankings: 1) select which documents human assessors should judge; and 2) automatically classify the relevance of additional unjudged documents. To assess our approach, we report experiments on five TREC collections with varying scarcity of relevant documents. We report labeling accuracy achieved, as well as rank correlation when evaluating participant systems based upon these labels vs. full pool judgments. Results show the effectiveness of our approach, and we further analyze how varying relevance scarcity across collections impacts our findings. To support reproducibility and follow-on work, we have shared our code online: https://github.com/mdmustafizurrahman/ICTIRALTestCollection2020/.