Copertina

Reliable Explanations or Random Noise? A Reliability Metric for XAI

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sengupta, Poushali, Maharjan, Sabita, Eliassen, Frank, Pandey, Shashi Raj, Zhang, Yan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Context Dependence and Reliability in Autoregressive Language Models
di: Sengupta, Poushali, et al.
Pubblicazione: (2026)

Correlation-Aware Feature Attribution Based Explainable AI
di: Sengupta, Poushali, et al.
Pubblicazione: (2025)

Explainability of Complex AI Models with Correlation Impact Ratio
di: Sengupta, Poushali, et al.
Pubblicazione: (2026)

Privacy-Utility-Fairness: A Balanced Approach to Vehicular-Traffic Management System
di: Sengupta, Poushali, et al.
Pubblicazione: (2025)

X-NegoBox: An Explainable Privacy-Budget Negotiation Framework for Secure Peer-to-Peer Energy Data Exchange
di: Sengupta, Poushali, et al.
Pubblicazione: (2026)

Adaptive Quantum-Safe Cryptography for 6G Vehicular Networks via Context-Aware Optimization
di: Sengupta, Poushali, et al.
Pubblicazione: (2026)

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

Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks
di: Zhang, Jiaxing, et al.
Pubblicazione: (2025)

Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance
di: Seth, Pratinav, et al.
Pubblicazione: (2025)

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

Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
di: Decker, Thomas, et al.
Pubblicazione: (2025)

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

LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
di: Cao, Zhuo, et al.
Pubblicazione: (2025)

BayesNAM: Leveraging Inconsistency for Reliable Explanations
di: Kim, Hoki, et al.
Pubblicazione: (2024)

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

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

CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine
di: Guo, Kevin H., et al.
Pubblicazione: (2026)

X-Node: Self-Explanation is All We Need
di: Sengupta, Prajit, et al.
Pubblicazione: (2025)

The Quest for Reliable Metrics of Responsible AI
di: Rampisela, Theresia Veronika, et al.
Pubblicazione: (2025)

Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations
di: Fresz, Benjamin, et al.
Pubblicazione: (2024)

Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
di: Schnake, Thomas, et al.
Pubblicazione: (2024)

CDKT-FL: Cross-Device Knowledge Transfer using Proxy Dataset in Federated Learning
di: Le, Huy Q., et al.
Pubblicazione: (2022)

PnPXAI: A Universal XAI Framework Providing Automatic Explanations Across Diverse Modalities and Models
di: Kim, Seongun, et al.
Pubblicazione: (2025)

Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration
di: Papanikou, Vasiliki, et al.
Pubblicazione: (2025)

Multi-Agent Conformal Prediction with Personalized Statistical Validity
di: Vejling, Martin V., et al.
Pubblicazione: (2026)

Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections
di: Zhang, Shiliang, et al.
Pubblicazione: (2026)

Are Sparse Autoencoder Benchmarks Reliable?
di: Chanin, David
Pubblicazione: (2026)

POEM: Explore Unexplored Reliable Samples to Enhance Test-Time Adaptation
di: Yi, Chang'an, et al.
Pubblicazione: (2025)

HistoLens: An Interactive XAI Toolkit for Verifying and Mitigating Flaws in Vision-Language Models for Histopathology
di: Vissapragada, Sandeep, et al.
Pubblicazione: (2025)

Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding
di: Baer, Gregor, et al.
Pubblicazione: (2026)

Stable Attention Response for Reliable Precipitation Nowcasting
di: Wen, Penghui, et al.
Pubblicazione: (2026)

Between Randomness and Arbitrariness: Some Lessons for Reliable Machine Learning at Scale
di: Cooper, A. Feder
Pubblicazione: (2024)

LLMs for XAI: Future Directions for Explaining Explanations
di: Zytek, Alexandra, et al.
Pubblicazione: (2024)

Towards Reliable Testing of Machine Unlearning
di: Mazhar, Anna, et al.
Pubblicazione: (2026)

Causally Reliable Concept Bottleneck Models
di: De Felice, Giovanni, et al.
Pubblicazione: (2025)

Reliable Conflictive Multi-View Learning
di: Xu, Cai, et al.
Pubblicazione: (2024)

Towards Reliable, Uncertainty-Aware Alignment
di: Banerjee, Debangshu, et al.
Pubblicazione: (2025)

Improving Predictor Reliability with Selective Recalibration
di: Zollo, Thomas P., et al.
Pubblicazione: (2024)

Evaluation Cards for XAI Metrics
di: Gipiškis, Rokas, et al.
Pubblicazione: (2026)

A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs
di: Mersha, Melkamu Abay, et al.
Pubblicazione: (2025)