No article text was recorded for this version.
explanation instability (explanation fragility)
Version 1 of 1271 papers330 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Robustness of Visual Explanations to Common Data Augmentation
- Blog: Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification
- Blog: Robustness of Visual Explanations to Common Data Augmentation Methods
- Blog: The Irrationality of Neural Rationale Models
- Blog: Fooling Explanations in Text Classifiers
- Blog: Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs
- Blog: Explainers in the Wild: Making Surrogate Explainers Robust to Distortions through Perception
- Blog: Improving Interpretation Faithfulness for Vision Transformers
- Blog: The (Un)reliability of Saliency Methods
- Blog: Applications of interpretable deep learning in neuroimaging: a comprehensive review
- Blog: ir_explain: A Python Library of Explainable IR Methods
- Blog: Estimating the Adversarial Robustness of Attributions in Text with Transformers
- Blog: Evaluating the robustness of explainable AI in medical image recognition under natural and adversarial data corruption
- Blog: How Sensitive are Sensitivity-Based Explanations?
- Blog: Probabilistic Stability Guarantees for Feature Attributions
- Blog: DRIVE: Dependable Robust Interpretable Visionary Ensemble Framework in Autonomous Driving
- Blog: Faithful Vision-Language Interpretation via Concept Bottleneck Models
- Blog: Habemus a Right to an Explanation: so What? – A Framework on Transparency-Explainability Functionality and Tensions in the EU AI Act
- Blog: Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution
- Blog: Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance
- Blog: Rethinking Explainability in the Era of Multimodal AI
- Blog: Feature Importance Depends on Properties of the Data: Towards Choosing the Correct Explanations for Your Data and Decision Trees based Models
- Blog: Stable Vision Concept Transformers for Medical Diagnosis
- Blog: When to Trust AI: Advances and Challenges for Certification of Neural Networks
- Blog: The (Un)reliability of saliency methods
- Blog: Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View
- Blog: Investigating the Impact of Model Instability on Explanations and Uncertainty
- Blog: Corrupting Neuron Explanations of Deep Visual Features
- Blog: Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing
- Blog: Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks
- Blog: Stability Guarantees for Feature Attributions with Multiplicative Smoothing
- Blog: The Irrationality of Neural Rationale Models
- Blog: Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training
- Blog: ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability
- Blog: XplainScreen: Unveiling the Black Box of Graph Neural Network Drug Screening Models with a Unified XAI Framework
- Blog: Estimating the Adversarial Robustness of Attributions in Text with Transformers
- Blog: Interpretation of Neural Networks is Fragile
- Blog: Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions
- Blog: OpenXAI: Towards a Transparent Evaluation of Model Explanations
- Blog: On the Lack of Robust Interpretability of Neural Text Classifiers
- Blog: Finding Representative Interpretations on Convolutional Neural Networks
- Blog: Logic Traps in Evaluating Attribution Scores
- Blog: Adversarial Attacks and Defenses in Explainable Artificial Intelligence: A Survey
- Blog: Explainers in the Wild: Making Surrogate Explainers Robust to Distortions Through Perception
- Blog: Training for Stable Explanation for Free
- Blog: When Can You Trust Your Explanations? A Robustness Analysis on Feature Importances
- Blog: Evaluating and Aggregating Feature-based Model Explanations
- Blog: On the Robustness of Removal-Based Feature Attributions
- Blog: Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
- Blog: EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models
- Blog: Robust Explanation Constraints for Neural Networks
- Blog: Pathologies of Neural Models Make Interpretations Difficult
- Blog: Analyzing the Effects of Classifier Lipschitzness on Explainers
- Blog: Explainers in the Wild: Making Surrogate Explainers Robust to Distortions Through Perception
- Blog: When Causal Intervention Meets Adversarial Examples and Image Masking for Deep Neural Networks
- Blog: Explanation Shift: How Did the Distribution Shift Impact the Model?
- Blog: On the Sensitivity and Stability of Model Interpretations in NLP
- Blog: Visual Explanations for Convolutional Neural Networks via Input Resampling
- Blog: Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets
- Blog: Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions
Showing 60 of 271 papers.
History & citation
Current · Permanent link
- Robustness and Reliability of Post-Hoc Explanations merged into this direction (51% overlap)
- Attributional Robustness for Stable Model Interpretability merged into this direction (70% overlap)
- Robust Feature Attribution for Trustworthy Machine Learning merged into this direction (77% overlap)
- Robustness and the Stability of Model Explanations merged into this direction (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_explanation_instability_explanation_frag_ba116733,
title = {explanation instability (explanation fragility)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/explanation-instability-explanation-fragility/rdr_ba11673308954e7f85f9a1d3c5fd9e85},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_explanation_instability_explanation_frag_ba116733_v1,
title = {explanation instability (explanation fragility)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/explanation-instability-explanation-fragility/rdr_ba11673308954e7f85f9a1d3c5fd9e85/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}