Copertina

In defence of post-hoc explanations in medical AI

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hatherley, Joshua, Munch, Lauritz, Bjerring, Jens Christian
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Human-Computer Interaction Artificial Intelligence Computers and Society Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A moving target in AI-assisted decision-making: Dataset shift, model updating, and the problem of update opacity
di: Hatherley, Joshua
Pubblicazione: (2025)

Federated learning, ethics, and the double black box problem in medical AI
di: Hatherley, Joshua, et al.
Pubblicazione: (2025)

Data over dialogue: Why artificial intelligence is unlikely to humanise medicine
di: Hatherley, Joshua
Pubblicazione: (2025)

High hopes for "Deep Medicine"? AI, economics, and the future of care
di: Sparrow, Robert, et al.
Pubblicazione: (2025)

Diachronic and synchronic variation in the performance of adaptive machine learning systems: The ethical challenges
di: Hatherley, Joshua, et al.
Pubblicazione: (2025)

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

Update Opacity: Epistemic Accessibility and Governance Under AI System Change
di: Ferrario, Andrea, et al.
Pubblicazione: (2026)

Limits of trust in medical AI
di: Hatherley, Joshua
Pubblicazione: (2025)

Are clinicians ethically obligated to disclose their use of medical machine learning systems to patients?
di: Hatherley, Joshua
Pubblicazione: (2025)

Rethinking AI Evaluation in Education: The TEACH-AI Framework and Benchmark for Generative AI Assistants
di: Ding, Shi, et al.
Pubblicazione: (2025)

Human-centered explanation does not fit all: The interplay of sociotechnical, cognitive, and individual factors in the effect AI explanations in algorithmic decision-making
di: Ahn, Yongsu, et al.
Pubblicazione: (2025)

Farsight: Fostering Responsible AI Awareness During AI Application Prototyping
di: Wang, Zijie J., et al.
Pubblicazione: (2024)

Personalizing explanations of AI-driven hints to users' characteristics: an empirical evaluation
di: Bahel, Vedant, et al.
Pubblicazione: (2024)

Generative AI in Medicine
di: Shanmugam, Divya, et al.
Pubblicazione: (2024)

A Nested Model for AI Design and Validation
di: Dubey, Akshat, et al.
Pubblicazione: (2024)

Human-in-the-Loop AI for Cheating Ring Detection
di: Shih, Yong-Siang, et al.
Pubblicazione: (2024)

Bringing Generative AI to Adaptive Learning in Education
di: Li, Hang, et al.
Pubblicazione: (2024)

Principles and Guidelines for Randomized Controlled Trials in AI Evaluation
di: Kelly, Christopher, et al.
Pubblicazione: (2026)

Narrowing Action Choices with AI Improves Human Sequential Decisions
di: Straitouri, Eleni, et al.
Pubblicazione: (2025)

From Melting Pots to Misrepresentations: Exploring Harms in Generative AI
di: Gautam, Sanjana, et al.
Pubblicazione: (2024)

Deterministic AI Agent Personality Expression through Standard Psychological Diagnostics
di: Kruijssen, J. M. Diederik, et al.
Pubblicazione: (2025)

The Evaluation Differential: When Frontier AI Models Recognise They Are Being Tested
di: Vishwarupe, Varad, et al.
Pubblicazione: (2026)

Ethics and Technical Aspects of Generative AI Models in Digital Content Creation
di: Karagoz, Atahan
Pubblicazione: (2024)

The Narcissus Hypothesis: Descending to the Rung of Illusion
di: Cadei, Riccardo, et al.
Pubblicazione: (2025)

The Digital Transformation in Health: How AI Can Improve the Performance of Health Systems
di: Periáñez, África, et al.
Pubblicazione: (2024)

AI Meets the Classroom: When Do Large Language Models Harm Learning?
di: Lehmann, Matthias, et al.
Pubblicazione: (2024)

AI-Enabled grading with near-domain data for scaling feedback with human-level accuracy
di: Agarwal, Shyam, et al.
Pubblicazione: (2025)

ff4ERA: A new Fuzzy Framework for Ethical Risk Assessment in AI
di: Dyoub, Abeer, et al.
Pubblicazione: (2025)

From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement
di: Vishwarupe, Varad, et al.
Pubblicazione: (2026)

AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia
di: Qadri, Rida, et al.
Pubblicazione: (2023)

Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings
di: Wolfe, Robert, et al.
Pubblicazione: (2024)

The Malicious Technical Ecosystem: Exposing Limitations in Technical Governance of AI-Generated Non-Consensual Intimate Images of Adults
di: Ding, Michelle L., et al.
Pubblicazione: (2025)

Culturally-Attuned Moral Machines: Implicit Learning of Human Value Systems by AI through Inverse Reinforcement Learning
di: Oliveira, Nigini, et al.
Pubblicazione: (2023)

Why am I Still Seeing This: Measuring the Effectiveness Of Ad Controls and Explanations in AI-Mediated Ad Targeting Systems
di: Castleman, Jane, et al.
Pubblicazione: (2024)

The AI Criminal Mastermind
di: Krook, Joshua
Pubblicazione: (2026)

Not someone, but something: Rethinking trust in the age of medical AI
di: Beger, Jan
Pubblicazione: (2025)

Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
di: Chiu, Yu Ying, et al.
Pubblicazione: (2025)

Talking Back -- human input and explanations to interactive AI systems
di: Dix, Alan, et al.
Pubblicazione: (2025)

When Autonomy Breaks: The Hidden Existential Risk of AI
di: Krook, Joshua
Pubblicazione: (2025)

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