No article text was recorded for this version.
explanation instability (stochastic explanation variance)
Version 2 of 2164 papers211 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Explanation Multiplicity in SHAP: Characterization and Assessment
- Blog: Using model explanations to guide deep learning models towards consistent explanations for EHR data
- Blog: To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods
- Blog: Benchmarking and survey of explanation methods for black box models
- Blog: Benchmark Analysis of Black Box Local Explanation Methods
- Blog: How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods
- Blog: Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP
- Blog: Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging
- Blog: What does LIME really see in images?
- Blog: Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations
- Blog: "Are Your Explanations Reliable?" Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack
- Blog: Explaining Deep Multi-Class Time Series Classifiers
- Blog: "Why Should You Trust My Explanation?" Understanding Uncertainty in LIME Explanations
- Blog: Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
- Blog: An empirical study of the effect of background data size on the stability of SHapley Additive exPlanations (SHAP) for deep learning models
- Blog: Quantifying Uncertainty in Natural Language Explanations of Large Language Models
- Blog: LFI-CAM: Learning Feature Importance for Better Visual Explanation
- Blog: Class-Specific Explainability for Deep Time Series Classifiers
- Blog: LEMON: Alternative Sampling for More Faithful Explanation Through Local Surrogate Models
- Blog: Explicability and Inexplicability in the Interpretation of Quantum Neural Networks
- Blog: Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection
- Blog: Revisiting Methods for Finding Influential Examples
- Blog: Uncertainty in Additive Feature Attribution methods
- Blog: Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learning
- Blog: Implications of Model Indeterminacy for Explanations of Automated Decisions
- Blog: S-LIME: Stabilized-LIME for Model Explanation
- Blog: Understanding Inter-Concept Relationships in Concept-Based Models
- Blog: Evaluating Input Perturbation Methods for Interpreting CNNs and Saliency Map Comparison
- Blog: Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection
- Blog: Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
- Blog: LFI-CAM: Learning Feature Importance for Better Visual Explanation
- Blog: Faithful and Fast Influence Function via Advanced Sampling
- Blog: On the Variability of Concept Activation Vectors
- Blog: Stabilizing Estimates of Shapley Values with Control Variates
- Blog: ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models
- Blog: Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning
- Blog: LEMON: Local Explanations via Modality-aware OptimizatioN
- Blog: EBLIME: Enhanced Bayesian Local Interpretable Model-agnostic Explanations
- Blog: Approximate information for efficient exploration-exploitation strategies
- Blog: Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression
- Blog: NA2Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning
- Blog: FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
- Blog: Stable graph based decision route explanation in siamese neural networks
- Blog: f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
- Blog: Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation
- Blog: BayesNAM: Leveraging Inconsistency for Reliable Explanations
- Blog: Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
- Blog: A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI
- Blog: Distributional Adversarial Loss
- Blog: Interactive Rationale Extraction for Text Classification
- Blog: Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AI
- Blog: CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows
- Blog: Interpreting Classifiers through Attribute Interactions in Datasets
- Blog: Ensemble Approaches for Graph Counterfactual Explanations
- Blog: Multi-Layer Attention-Based Explainability via Transformers for Tabular Data
- Blog: Transparent Neighborhood Approximation for Text Classifier Explanation
- Blog: XPROAX-Local explanations for text classification with progressive neighborhood approximation
- Blog: On the Robustness of Interpretability Methods
- Blog: A Multilinear Sampling Algorithm to Estimate Shapley Values
- Blog: Efficient and Accurate Explanation Estimation with Distribution Compression
Showing 60 of 164 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_explanation_instability_stochastic_expla_5a30a1d8,
title = {explanation instability (stochastic explanation variance)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/explanation-instability-stochastic-explanation-variance/rdr_5a30a1d81e74435b99c487e2b53968de},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_explanation_instability_stochastic_expla_5a30a1d8_v2,
title = {explanation instability (stochastic explanation variance)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/explanation-instability-stochastic-explanation-variance/rdr_5a30a1d81e74435b99c487e2b53968de/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}