Imagen de Portada

Introducing δ-XAI: a novel sensitivity-based method for local AI explanations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	De Carlo, Alessandro, Parimbelli, Enea, Melillo, Nicola, Nicora, Giovanna
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How can we trust opaque systems? Criteria for robust explanations in XAI
por: Boge, Florian J., et al.
Publicado: (2025)

Dual feature-based and example-based explanation methods
por: Konstantinov, Andrei V., et al.
Publicado: (2024)

Why do explanations fail? A typology and discussion on failures in XAI
por: Bove, Clara, et al.
Publicado: (2024)

Towards a perturbation-based explanation for medical AI as differentiable programs
por: Abe, Takeshi, et al.
Publicado: (2025)

Toward the application of XAI methods in EEG-based systems
por: Apicella, Andrea, et al.
Publicado: (2022)

Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science
por: Bommer, Philine, et al.
Publicado: (2023)

CHILLI: A data context-aware perturbation method for XAI
por: Anwar, Saif, et al.
Publicado: (2024)

Axe the X in XAI: A Plea for Understandable AI
por: Páez, Andrés
Publicado: (2024)

Evaluation of Predictive Reliability to Foster Trust in Artificial Intelligence. A case study in Multiple Sclerosis
por: Peracchio, Lorenzo, et al.
Publicado: (2024)

EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods
por: Clark, Benedict, et al.
Publicado: (2024)

The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations
por: Swamy, Vinitra, et al.
Publicado: (2023)

Model Science: getting serious about verification, explanation and control of AI systems
por: Biecek, Przemyslaw, et al.
Publicado: (2025)

Overcoming Anchoring Bias: The Potential of AI and XAI-based Decision Support
por: Haag, Felix, et al.
Publicado: (2024)

A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring
por: Fontanesi, Michele, et al.
Publicado: (2025)

Mind the XAI Gap: A Human-Centered LLM Framework for Democratizing Explainable AI
por: Paraschou, Eva, et al.
Publicado: (2025)

PAX-TS: Model-agnostic multi-granular explanations for time series forecasting via localized perturbations
por: Kreuzer, Tim, et al.
Publicado: (2025)

Introducing User Feedback-based Counterfactual Explanations (UFCE)
por: Suffian, Muhammad, et al.
Publicado: (2024)

Local Universal Explainer (LUX) -- a rule-based explainer with factual, counterfactual and visual explanations
por: Bobek, Szymon, et al.
Publicado: (2023)

PSO-XAI: A PSO-Enhanced Explainable AI Framework for Reliable Breast Cancer Detection
por: Raquib, Mirza, et al.
Publicado: (2025)

ExplainReduce: Generating global explanations from many local explanations
por: Seppäläinen, Lauri, et al.
Publicado: (2025)

A Mechanistic Explanatory Strategy for XAI
por: Rabiza, Marcin
Publicado: (2024)

Towards plausibility in time series counterfactual explanations
por: Kostrzewa, Marcin, et al.
Publicado: (2026)

On the Hardness of Computing Counterfactual and Semifactual Explanations in XAI
por: Artelt, André, et al.
Publicado: (2026)

OpenXAI: Towards a Transparent Evaluation of Model Explanations
por: Agarwal, Chirag, et al.
Publicado: (2022)

A Bayesian explanation of machine learning models based on modes and functional ANOVA
por: Long, Quan
Publicado: (2024)

Towards consistency of rule-based explainer and black box model -- fusion of rule induction and XAI-based feature importance
por: Kozielski, Michał, et al.
Publicado: (2024)

XAI-Units: Benchmarking Explainability Methods with Unit Tests
por: Lee, Jun Rui, et al.
Publicado: (2025)

In defence of post-hoc explanations in medical AI
por: Hatherley, Joshua, et al.
Publicado: (2025)

Actionable and diverse counterfactual explanations incorporating domain knowledge and plausibility constraints
por: Bobek, Szymon, et al.
Publicado: (2025)

IMPACTX: improving model performance by appropriately constraining the training with teacher explanations
por: Apicella, Andrea, et al.
Publicado: (2025)

HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data
por: Marszałek, Patryk, et al.
Publicado: (2025)

STRIDE: Subset-Free Functional Decomposition for XAI in Tabular Settings
por: Ko, Chaeyun
Publicado: (2025)

Reliable Explanations or Random Noise? A Reliability Metric for XAI
por: Sengupta, Poushali, et al.
Publicado: (2026)

Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefer
por: Aryal, Saugat, et al.
Publicado: (2026)

XAI for In-hospital Mortality Prediction via Multimodal ICU Data
por: Li, Xingqiao, et al.
Publicado: (2023)

Explainable AI Through a Democratic Lens: DhondtXAI for D'Hondt-Projected Feature Attribution
por: Donmez, Turker Berk
Publicado: (2024)

Making deep neural networks right for the right scientific reasons by interacting with their explanations
por: Schramowski, Patrick, et al.
Publicado: (2020)

Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective
por: Xiong, Haoyi, et al.
Publicado: (2024)

Explaining deep neural network models for electricity price forecasting with XAI
por: Pesenti, Antoine, et al.
Publicado: (2025)

Improving Health Professionals' Onboarding with AI and XAI for Trustworthy Human-AI Collaborative Decision Making
por: Lee, Min Hun, et al.
Publicado: (2024)