PulseAugur
EN
LIVE 06:27:29

AI explainability in medicine faces philosophical critique · 3 sources tracked

By PulseAugur Editorial · [3 sources] ·

A new paper explores the philosophical underpinnings of explainability in medical AI, arguing that current approaches in explainable AI (XAI) overlook crucial insights from the philosophy of science and medicine. The research emphasizes the need to integrate causality, trust, and epistemic adequacy into XAI systems for clinical decision-making. Another related paper questions the reliability of post-hoc explanations for opaque scientific models, stating that faithfulness and reliability checks do not guarantee that the model accurately reflects the underlying phenomenon. AI

IMPACT Critiques current AI explainability methods, suggesting a need for deeper philosophical grounding in scientific applications.

RANK_REASON Cluster consists of two academic papers discussing AI explainability in scientific contexts.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

AI explainability in medicine faces philosophical critique · 3 sources tracked

COVERAGE [3]

  1. arXiv cs.AI TIER_1 English(EN) · Martina Mattioli, Marcello Pelillo ·

    Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy

    arXiv:2606.31616v1 Announce Type: new Abstract: Medical Artificial Intelligence (AI) is widely expected to transform clinical practice, yet the decision-making processes of many Machine Learning (ML) models remain opaque. Explainability has been advanced as a partial remedy to cl…

  2. arXiv cs.AI TIER_1 English(EN) · Marcello Pelillo ·

    Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy

    Medical Artificial Intelligence (AI) is widely expected to transform clinical practice, yet the decision-making processes of many Machine Learning (ML) models remain opaque. Explainability has been advanced as a partial remedy to clarify why AI generates predictions, particularly…

  3. arXiv cs.LG TIER_1 English(EN) · Nick Oh, Helen Jin ·

    Reliability, Faithfulness, and the Limits of Post-hoc Explanations of Opaque Scientific Models

    arXiv:2606.29346v1 Announce Type: new Abstract: Post-hoc explanation methods are routinely used to interpret scientific machine learning models, with the deliverable understood to be insight into the phenomenon the model has been trained on. The transition may be taken to be secu…

RELATED ENTITIES

RELATED TOPICS