# White-box Testing of NLP models with Mask Neuron Coverage

arXiv: https://arxiv.org/abs/2205.05050 · HTML: https://mlsanity.com/paper/2205.05050/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 10 May 2022.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Stress Test Evaluation for Natural Language Inference](https://mlsanity.com/paper/1806.00692/) (2018)
- [DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems](https://mlsanity.com/paper/1803.07519/) (2018)
- [Perturbation Sensitivity Analysis to Detect Unintended Model Biases](https://mlsanity.com/paper/1910.04210/) (2019)
- [Distribution-Aware Testing of Neural Networks Using Generative Models](https://mlsanity.com/paper/2102.13602/) (2021)
- [Combinatorial Testing for Deep Learning Systems](https://mlsanity.com/paper/1806.07723/) (2018)

## Built on by (most cited first, 2 of 2)

- [Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench](https://mlsanity.com/paper/2308.03656/) (2023)
- [Influence-Guided Concolic Testing of Transformer Robustness](https://mlsanity.com/paper/2509.23806/) (2025)

## Abstract (arXiv)

Recent literature has seen growing interest in using black-box strategies like CheckList for testing the behavior of NLP models. Research on white-box testing has developed a number of methods for evaluating how thoroughly the internal behavior of deep models is tested, but they are not applicable to NLP models. We propose a set of white-box testing methods that are customized for transformer-based NLP models. These include Mask Neuron Coverage (MNCOVER) that measures how thoroughly the attention layers in models are exercised during testing. We show that MNCOVER can refine testing suites generated by CheckList by substantially reduce them in size, for more than 60% on average, while retaining failing tests -- thereby concentrating the fault detection power of the test suite. Further we show how MNCOVER can be used to guide CheckList input generation, evaluate alternative NLP testing methods, and drive data augmentation to improve accuracy.