No article text was recorded for this version.
hyperparameter sensitivity (explanation instability)
Version 2 of 234 papers44 conceptsfrozen 2026-10-04
Papers in this version
- Blog: From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation
- Blog: SAM: The Sensitivity of Attribution Methods to Hyperparameters
- Blog: On the Relationship Between Explanation and Prediction: A Causal View
- Blog: Hyperparameters and Tuning Strategies for Random Forest
- Blog: Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance
- Blog: An Empirical Comparison of Explainable Artificial Intelligence Methods for Clinical Data: A Case Study on Traumatic Brain Injury
- Blog: The Price of Freedom: An Adversarial Attack on Interpretability Evaluation
- Blog: Evaluating the Ability of Explanations to Disambiguate Models in a Rashomon Set
- Blog: Interpretable Geometric Deep Learning via Learnable Randomness Injection
- Blog: Towards Interpretation of Pairwise Learning
- Blog: Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks
- Blog: Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
- Blog: Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanations
- Blog: An Adversarial Approach for Explaining the Predictions of Deep Neural Networks
- Blog: What does LIME really see in images?
- Blog: BELIEF - Bayesian Sign Entropy Regularization for LIME Framework
- Blog: Challenges in explaining deep learning models for data with biological variation
- Blog: An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning
- Blog: Efficient computation of counterfactual explanations of LVQ models
- Blog: DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
- Blog: Gradient-free Post-hoc Explainability Using Distillation Aided Learnable Approach
- Blog: The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus
- Blog: Evaluating Link Prediction Explanations for Graph Neural Networks
- Blog: Iterative Search Attribution for Deep Neural Networks
- Blog: Representer Point Selection via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models
- Blog: Optimal Information Retention for Time-Series Explanations
- Blog: Evaluating Input Perturbation Methods for Interpreting CNNs and Saliency Map Comparison
- Blog: Interpretable correlator Transformer for image-like quantum matter data
- Blog: Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification
- Blog: Probabilistic Stability Guarantees for Feature Attributions
- Blog: A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines
- Blog: Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
- Blog: How can I choose an explainer?: An Application-grounded Evaluation of Post-hoc Explanations
- Blog: AttEXplore: Attribution for Explanation with model parameters eXploration
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_hyperparameter_sensitivity_explanation_i_14d81ea6,
title = {hyperparameter sensitivity (explanation instability)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hyperparameter-sensitivity-explanation-instability/rdr_14d81ea6ba174d38a0459b7b041a59a3},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_hyperparameter_sensitivity_explanation_i_14d81ea6_v2,
title = {hyperparameter sensitivity (explanation instability)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hyperparameter-sensitivity-explanation-instability/rdr_14d81ea6ba174d38a0459b7b041a59a3/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}