Cover Image

How can we trust opaque systems? Criteria for robust explanations in XAI

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Boge, Florian J., Schuster, Annika
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Who can we trust? LLM-as-a-jury for Comparative Assessment
by: Qian, Mengjie, et al.
Published: (2026)

Introducing δ-XAI: a novel sensitivity-based method for local AI explanations
by: De Carlo, Alessandro, et al.
Published: (2024)

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

Can we trust the evaluation on ChatGPT?
by: Aiyappa, Rachith, et al.
Published: (2023)

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

Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?
by: Kaufmann, Max, et al.
Published: (2026)

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

Are we still able to recognize pearls? Machine-driven peer review and the risk to creativity: An explainable RAG-XAI detection framework with markers extraction
by: Văduva, Alin-Gabriel, et al.
Published: (2026)

How Reliable and Stable are Explanations of XAI Methods?
by: Ribeiro, José, et al.
Published: (2024)

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

How adversarial attacks can disrupt seemingly stable accurate classifiers
by: Sutton, Oliver J., et al.
Published: (2023)

A Mechanistic Explanatory Strategy for XAI
by: Rabiza, Marcin
Published: (2024)

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

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

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

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

Can I trust my anomaly detection system? A case study based on explainable AI
by: Rashid, Muhammad, et al.
Published: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Which LIME should I trust? Concepts, Challenges, and Solutions
by: Knab, Patrick, et al.
Published: (2025)

Modular addition without black-boxes: Compressing explanations of MLPs that compute numerical integration
by: Yip, Chun Hei, et al.
Published: (2024)

Guiding the generation of counterfactual explanations through temporal background knowledge for Predictive Process Monitoring
by: Buliga, Andrei, et al.
Published: (2024)

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

Limits of trust in medical AI
by: Hatherley, Joshua
Published: (2025)

A multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainers
by: Stępka, Ignacy, et al.
Published: (2024)

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

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