Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation

Chong Zhang, Jieyu Zhao, Huan Zhang, Kai-Wei Chang, Cho-Jui Hsieh


Abstract
Robustness and counterfactual bias are usually evaluated on a test dataset. However, are these evaluations robust? If the test dataset is perturbed slightly, will the evaluation results keep the same? In this paper, we propose a “double perturbation” framework to uncover model weaknesses beyond the test dataset. The framework first perturbs the test dataset to construct abundant natural sentences similar to the test data, and then diagnoses the prediction change regarding a single-word substitution. We apply this framework to study two perturbation-based approaches that are used to analyze models’ robustness and counterfactual bias in English. (1) For robustness, we focus on synonym substitutions and identify vulnerable examples where prediction can be altered. Our proposed attack attains high success rates (96.0%-99.8%) in finding vulnerable examples on both original and robustly trained CNNs and Transformers. (2) For counterfactual bias, we focus on substituting demographic tokens (e.g., gender, race) and measure the shift of the expected prediction among constructed sentences. Our method is able to reveal the hidden model biases not directly shown in the test dataset. Our code is available at https://github.com/chong-z/nlp-second-order-attack.
Anthology ID:
2021.naacl-main.305
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3899–3916
Language:
URL:
https://aclanthology.org/2021.naacl-main.305
DOI:
10.18653/v1/2021.naacl-main.305
Bibkey:
Cite (ACL):
Chong Zhang, Jieyu Zhao, Huan Zhang, Kai-Wei Chang, and Cho-Jui Hsieh. 2021. Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3899–3916, Online. Association for Computational Linguistics.
Cite (Informal):
Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation (Zhang et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.305.pdf
Video:
 https://aclanthology.org/2021.naacl-main.305.mp4
Code
 chong-z/nlp-second-order-attack
Data
GLUESSTSST-2