# Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification

arXiv: https://arxiv.org/abs/2212.05327 · HTML: https://mlsanity.com/paper/2212.05327/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 55 references that are in the map.
- First posted on arXiv 10 Dec 2022.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [Techniques for Interpretable Machine Learning](https://mlsanity.com/paper/1808.00033/) (2018)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [To Trust Or Not To Trust A Classifier](https://mlsanity.com/paper/1805.11783/) (2018)
- [Generating Natural Adversarial Examples](https://mlsanity.com/paper/1710.11342/) (2017)
- [Certified Robustness to Adversarial Word Substitutions](https://mlsanity.com/paper/1909.00986/) (2019)
- [Fooling Neural Network Interpretations via Adversarial Model Manipulation](https://mlsanity.com/paper/1902.02041/) (2019)
- [Adversarial Training for Large Neural Language Models](https://mlsanity.com/paper/2004.08994/) (2020)
- [Deep Text Classification Can be Fooled](https://mlsanity.com/paper/1704.08006/) (2017)
- [L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data](https://mlsanity.com/paper/1808.02610/) (2018)
- [Interpretable Deep Learning under Fire](https://mlsanity.com/paper/1812.00891/) (2018)
- [Robust Attribution Regularization](https://mlsanity.com/paper/1905.09957/) (2019)

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

- [Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions](https://mlsanity.com/paper/2406.04606/) (2024)
- [Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training](https://mlsanity.com/paper/2312.17591/) (2023)

## Abstract (arXiv)

Some recent works observed the instability of post-hoc explanations when input side perturbations are applied to the model. This raises the interest and concern in the stability of post-hoc explanations. However, the remaining question is: is the instability caused by the neural network model or the post-hoc explanation method? This work explores the potential source that leads to unstable post-hoc explanations. To separate the influence from the model, we propose a simple output probability perturbation method. Compared to prior input side perturbation methods, the output probability perturbation method can circumvent the neural model's potential effect on the explanations and allow the analysis on the explanation method. We evaluate the proposed method with three widely-used post-hoc explanation methods (LIME (Ribeiro et al., 2016), Kernel Shapley (Lundberg and Lee, 2017a), and Sample Shapley (Strumbelj and Kononenko, 2010)). The results demonstrate that the post-hoc methods are stable, barely producing discrepant explanations under output probability perturbations. The observation suggests that neural network models may be the primary source of fragile explanations.