PulseAugur
实时 07:51:31
English(EN) Reliability, Faithfulness, and the Limits of Post-hoc Explanations of Opaque Scientific Models

人工智能在医学中的可解释性面临哲学批判 · 跟踪 3 个来源

一篇新论文探讨了医学人工智能中可解释性的哲学基础,认为当前可解释人工智能 (XAI) 的方法忽略了科学和医学哲学中的关键见解。该研究强调,在临床决策中,需要将因果关系、信任和认识论充分性整合到 XAI 系统中。另一篇相关论文质疑了不透明科学模型的事后解释的可靠性,指出忠实性和可靠性检查不能保证模型准确地反映潜在现象。 AI

影响 批判了当前的人工智能可解释性方法,表明在科学应用中需要更深层次的哲学基础。

排序理由 该集群包含两篇讨论科学背景下人工智能可解释性的学术论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

人工智能在医学中的可解释性面临哲学批判 · 跟踪 3 个来源

报道来源 [3]

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

    健康科学中的科学解释:因果关系、信任与认识论充分性

    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 ·

    健康科学中的科学解释:因果关系、信任与认识论充分性

    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 ·

    不透明科学模型的事后解释的可靠性、忠实性及其局限性

    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…