Nothing Special   »   [go: up one dir, main page]

“Are Your Explanations Reliable?” Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack

Christopher Burger, Lingwei Chen, Thai Le


Abstract
LIME has emerged as one of the most commonly referenced tools in explainable AI (XAI) frameworks that is integrated into critical machine learning applications (e.g., healthcare and finance). However, its stability remains little explored, especially in the context of text data, due to the unique text-space constraints. To address these challenges, in this paper, we first evaluate the inherent instability of LIME on text data to establish a baseline, and then propose a novel algorithm XAIFooler to perturb text inputs and manipulate explanations that casts investigation on the stability of LIME as a text perturbation optimization problem. XAIFooler conforms to the constraints to preserve text semantics and original prediction with small perturbations, and introduces Rank-biased Overlap (RBO) as a key part to guide the optimization of XAIFooler that satisfies all the requirements for explanation similarity measure. Extensive experiments on real-world text datasets demonstrate that XAIFooler significantly outperforms all baselines by large margins in its ability to manipulate LIME’s explanations with high semantic preservability.
Anthology ID:
2023.emnlp-main.792
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12831–12844
Language:
URL:
https://aclanthology.org/2023.emnlp-main.792
DOI:
10.18653/v1/2023.emnlp-main.792
Bibkey:
Cite (ACL):
Christopher Burger, Lingwei Chen, and Thai Le. 2023. “Are Your Explanations Reliable?” Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12831–12844, Singapore. Association for Computational Linguistics.
Cite (Informal):
“Are Your Explanations Reliable?” Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack (Burger et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.792.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.792.mp4