paper-with-me

Papers

Select, Label, Evaluate: Active Testing in NLP

2026-03-23 · Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu, Amin Mantrach, Fabrizio Silvestri arxiv

Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-error and high-quality labels necessary for reliable model evaluation. Traditional approaches require annotating entire test sets, leading to substantial resource requirements. Active Testing is a framework that selects the most informative test samples for annotation. Given a labeling budget, it aims to choose the subset that best estimates model performance while minimizing cost and human effort. In this work, we formalize Active Testing in NLP and we conduct an extensive benchmarking of existing approaches across 18 datasets and 4 embedding strategies spanning 4 different NLP tasks. The experiments show annotation reductions of up to 95%, with performance estimation accuracy difference from the full test set within 1%. Our analysis reveals variations in method effectiveness across different data characteristics and task types, with no single approach emerging as universally superior. Lastly, to address the limitation of requiring a predefined annotation budget in existing sample selection strategies, we introduce an adaptive stopping criterion that automatically determines the optimal number of samples. We release our code at https://github.com/amazon-science/NLPActiveTesting.

📄 PDF Abstract BibTeX arXiv:2603.21840

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Active Testing: Sample-Efficient Model Evaluation

2021-03-09 · Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth

We introduce a new framework for sample-efficient model evaluation that we call active testing. While approaches like active learning reduce the number of labels needed for model training, existing literature largely ign…

Active LearningGaussian Processesmodel

Advanced Tutorial: Label-Efficient Two-Sample Tests

2025-01-07 · Weizhi Li, Visar Berisha, Gautam Dasarathy

Hypothesis testing is a statistical inference approach used to determine whether data supports a specific hypothesis. An important type is the two-sample test, which evaluates whether two sets of data points are from ide…

Active LearningTwo-sample testing

Active Sequential Two-Sample Testing

2023-01-30 · Weizhi Li, Prad Kadambi, Pouria Saidi, Karthikeyan Natesan Ramamurthy 외

A two-sample hypothesis test is a statistical procedure used to determine whether the distributions generating two samples are identical. We consider the two-sample testing problem in a new scenario where the sample meas…

Two-sample testingvalidVocal Bursts Valence Prediction

Prediction-Powered Active Testing

2026-07-09 · Kianoosh Ashouritaklimi, Valentin Kilian, Daolang Huang, Tom Rainforth 외 arxiv

Active testing provides a label--efficient approach to risk estimation by adaptively selecting which test points should be labelled. However, existing estimators fail to exploit the informative predictions of powerful bl…

Generative Active Testing: Efficient LLM Evaluation via Proxy Task Adaptation

2026-02-26 · Aashish Anantha Ramakrishnan, Ardavan Saeedi, Hamid Reza Hassanzadeh, Fazlolah Mohaghegh 외 arxiv

With the widespread adoption of pre-trained Large Language Models (LLM), there exists a high demand for task-specific test sets to benchmark their performance in domains such as healthcare and biomedicine. However, the c…

Generative Question Answering