A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Julia Amann, Alessandro Blasimme, Effy Vayena, et al.
A multidisciplinary ethical analysis showing that explainability in medical AI is essential to core biomedical principles and clinical adoption.
Unknown
This paper introduces a Graph RAG approach that integrates Knowledge Graphs and LLMs to contextualize and enrich user requests for dataset discovery, enhancing explainability.
Johannes Schneider
A survey and conceptualization of explainability for generative AI, introducing new criteria and a research agenda.
Nadia Burkart, Marco F. Huber
A comprehensive survey defining and categorizing explainability methods for supervised machine learning, with a case study and future directions.
Rudresh Dwivedi, Devam Dave, Het Naik, et al.
A comprehensive survey of XAI techniques, taxonomies, and programming frameworks to guide stakeholders in selecting appropriate explainability methods.
Ribana Roscher, Bastian Bohn, Marco F. Duarte, et al.
Reviews explainable machine learning for scientific discovery, emphasizing transparency, interpretability, and explainability with domain knowledge.
Haiyan Zhao, Hanjie Chen, Fan Yang, et al.
A structured survey of explainability techniques for Transformer-based LLMs, categorizing methods by fine-tuning and prompting paradigms.
Lukas Ruff, Jacob R. Kauffmann, Robert A. Vandermeulen, et al.
This review unifies deep and shallow anomaly detection methods, identifies common principles, and provides empirical assessment with explainability.
Andreas Holzinger, Georg Langs, Helmut Denk, et al.
The paper introduces 'causability' as a human property for measuring explanation quality, distinct from explainability as a system property, to advance explainable medicine.
Wojciech Samek, Grégoire Montavon, Sebastian Lapuschkin, et al.
A comprehensive review of post-hoc explainability methods for deep neural networks, covering theory, comparative evaluation, best practices, and applications.