Arshdeep Sekhon


2022

pdf bib
White-box Testing of NLP models with Mask Neuron Coverage
Arshdeep Sekhon | Yangfeng Ji | Matthew Dwyer | Yanjun Qi
Findings of the Association for Computational Linguistics: NAACL 2022

Recent literature has seen growing interest in using black-box strategies like for testing the behavior of NLP models. Research on white-box testing has developed a number of methods for evaluatinghow thoroughly the internal behavior of deep models is tested, but they are not applicableto 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 thoroughlythe attention layers in models are exercised during testing. We show that MNCOVER can refine testing suites generated by CheckList by substantiallyreduce them in size, for more than 60% on average, while retaining failing tests – thereby concentrating the faultdetection power of the test suite. Further we show how can be used to guide CheckList input generation,evaluate alternative NLP testing methods, and drive data augmentation to improve accuracy.

2021

pdf bib
Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing
Sanchit Sinha | Hanjie Chen | Arshdeep Sekhon | Yangfeng Ji | Yanjun Qi
Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

Interpretability methods like Integrated Gradient and LIME are popular choices for explaining natural language model predictions with relative word importance scores. These interpretations need to be robust for trustworthy NLP applications in high-stake areas like medicine or finance. Our paper demonstrates how interpretations can be manipulated by making simple word perturbations on an input text. Via a small portion of word-level swaps, these adversarial perturbations aim to make the resulting text semantically and spatially similar to its seed input (therefore sharing similar interpretations). Simultaneously, the generated examples achieve the same prediction label as the seed yet are given a substantially different explanation by the interpretation methods. Our experiments generate fragile interpretations to attack two SOTA interpretation methods, across three popular Transformer models and on three different NLP datasets. We observe that the rank order correlation and top-K intersection score drops by over 20% when less than 10% of words are perturbed on average. Further, rank-order correlation keeps decreasing as more words get perturbed. Furthermore, we demonstrate that candidates generated from our method have good quality metrics.