Hugging Face Trending Papers
Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
Aug 25
Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality
arXiv:2608.23164v1 Announce Type: cross Abstract: Counterfactual (CF) explanations for time-series classifiers are usually evaluated one example at a time: what minimal edit flips this single window'...
arXiv Computer Vision
2d ago
Towards Fast and Disentangled Counterfactuals for Visual Foundation Models
arXiv:2610.00895v1 Announce Type: cross Abstract: Foundation models remain vulnerable to spurious correlations and ``Clever Hans'' strategies. Explainable machine learning can find and remove such st...
arXiv AI
6d ago
Robust to Which Model Change? A Unified Evaluation of Robust Counterfactual Explanations
The paper introduces a unified evaluation protocol for robust counterfactual explanations (CFE), testing six robust methods and two baselines across four tabular datasets under eight types of model change. It shows that robustness scores vary by change type and that methods designed for one change family may not transfer to others, with RobX performing most consistently. The study emphasizes the need for a common protocol that defines model changes, measures their impact, and separates generation performance from robustness.
arXiv Machine Learning
Jul 9
Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
arXiv:2607. 06637v1 Announce Type: new Abstract: In this work, we propose a unified approach for diagnosing misclassification and assessing the robustness of black-box classifiers.
arXiv Machine Learning
Jun 4
A Geometric View of Counterfactual Behavior: Interaction of Boundary Proximity and Local Support
arXiv:2606. 04209v1 Announce Type: new Abstract: Counterfactual explanations seek small, semantically meaningful changes to an input that alter a model's prediction, and are widely used to interpret and audit machine learning systems.
arXiv AI
Aug 11
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
arXiv:2603. 22016v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verification, repeated attempts, or unnecessary exploration that wastes computation and can even overturn the correct answer.