Image de couverture de livre

Informative Post-Hoc Explanations Only Exist for Simple Functions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Günther, Eric, Szabados, Balázs, Bhattacharjee, Robi, Bordt, Sebastian, von Luxburg, Ulrike
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

How to safely discard features based on aggregate SHAP values
par: Bhattacharjee, Robi, et autres
Publié: (2025)

Auditing Local Explanations is Hard
par: Bhattacharjee, Robi, et autres
Publié: (2024)

On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
par: Haas, Moritz, et autres
Publié: (2025)

How Much Can We Forget about Data Contamination?
par: Bordt, Sebastian, et autres
Publié: (2024)

Rethinking Explainable Machine Learning as Applied Statistics
par: Bordt, Sebastian, et autres
Publié: (2024)

The Manifold Hypothesis for Gradient-Based Explanations
par: Bordt, Sebastian, et autres
Publié: (2022)

Train Once, Answer All: Many Pretraining Experiments for the Cost of One
par: Bordt, Sebastian, et autres
Publié: (2025)

Using predictive multiplicity to measure individual performance within the AI Act
par: Frohnapfel, Karolin, et autres
Publié: (2026)

ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models
par: Huang, Bosong, et autres
Publié: (2025)

Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations
par: Tan, Zhen, et autres
Publié: (2025)

Disentangling Interactions and Dependencies in Feature Attribution
par: König, Gunnar, et autres
Publié: (2024)

xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods
par: Seth, Pratinav, et autres
Publié: (2025)

SHapley Estimated Explanation (SHEP): A Fast Post-Hoc Attribution Method for Interpreting Intelligent Fault Diagnosis
par: Chen, Qian, et autres
Publié: (2025)

Post Hoc Regression Refinement via Pairwise Rankings
par: Wijaya, Kevin Tirta, et autres
Publié: (2025)

Post-Hoc Reversal: Are We Selecting Models Prematurely?
par: Ranjan, Rishabh, et autres
Publié: (2024)

Smooth InfoMax -- Towards Easier Post-Hoc Interpretability
par: Denoodt, Fabian, et autres
Publié: (2024)

Agent-Based Post-Hoc Correction of Agricultural Yield Forecasts
par: Beddows, Matthew, et autres
Publié: (2026)

Fuzzy Logic Function as a Post-hoc Explanator of the Nonlinear Classifier
par: Klimo, Martin, et autres
Publié: (2024)

Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classification
par: Yuan, Han, et autres
Publié: (2024)

Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations
par: Chugh, Sumedha, et autres
Publié: (2026)

CalArena: A Large-Scale Post-Hoc Calibration Benchmark
par: Berta, Eugène, et autres
Publié: (2026)

Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining
par: Abro, Aarash, et autres
Publié: (2026)

Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models
par: Bordt, Sebastian, et autres
Publié: (2024)

Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networks
par: Bramlage, Lennart, et autres
Publié: (2025)

Operationalizing Fairness: Post-Hoc Threshold Optimization Under Hard Resource Limits
par: Singh, Moirangthem Tiken, et autres
Publié: (2026)

Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations
par: Erogullari, Eren, et autres
Publié: (2025)

Beyond Simple Graphs: Neural Multi-Objective Routing on Multigraphs
par: Rydin, Filip, et autres
Publié: (2025)

DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs
par: Luo, Yingsong, et autres
Publié: (2024)

Unifying Post-hoc Explanations of Knowledge Graph Completions
par: Lonardi, Alessandro, et autres
Publié: (2025)

TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models
par: Tang, Yuchi, et autres
Publié: (2025)

ChaosMining: A Benchmark to Evaluate Post-Hoc Local Attribution Methods in Low SNR Environments
par: Shi, Ge, et autres
Publié: (2024)

Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection
par: Šarčević, Antonia, et autres
Publié: (2026)

Enhancing Machine Learning Performance through Intelligent Data Quality Assessment: An Unsupervised Data-centric Framework
par: Rahal, Manal, et autres
Publié: (2025)

Performative Validity of Recourse Explanations
par: König, Gunnar, et autres
Publié: (2025)

Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
par: Xia, Yifan, et autres
Publié: (2024)

EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models
par: Dhaini, Mahdi, et autres
Publié: (2025)

Calibrated Explanations: with Uncertainty Information and Counterfactuals
par: Lofstrom, Helena, et autres
Publié: (2023)

Deep Backtracking Counterfactuals for Causally Compliant Explanations
par: Kladny, Klaus-Rudolf, et autres
Publié: (2023)

Unifying Attribution-Based Explanations Using Functional Decomposition
par: Gevaert, Arne, et autres
Publié: (2024)

Symmetry-Breaking Augmentations for Ad Hoc Teamwork
par: Hammond, Ravi, et autres
Publié: (2024)