Machine learning models that offer excellent predictive performance often lack the interpretability necessary to support integrated human machine decision-making. In clinical medicine and other high-risk settings, domain experts may be unwilling to trust model predictions without explanations. Work in explainable AI must balance competing objectives along two different axes: 1) Explanations must balance faithfulness to the model's decision-making with their plausibility to a domain expert. 2) Domain experts desire local explanations of individual predictions and global explanations of behavior in aggregate. We propose to train a proxy model that mimics the behavior of the trained model and provides fine-grained control over these trade-offs. We evaluate our approach on the task of assigning ICD codes to clinical notes to demonstrate that explanations from the proxy model are faithful and replicate the trained model behavior.
Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning
Stratified Precision；Harvard Medical School（哈佛医学院）；Imperial College London（帝国理工学院伦敦分校）；National Health Service（国家健康服务系统）；Ipsen France（Ipsen法国）；University College London（伦敦大学学院）
Topologically Faithful Multi-class Segmentation in Medical Images
School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich（慕尼黑工业大学伊萨尔河畔 Klinikum 医学院与健康学院）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Munich Data Science Institute, Technical University of Munich（慕尼黑工业大学慕尼黑数据科学研究所）；Department of Quantitative Biomedicine, University of Zurich（苏黎世大学定量生物医学系）
Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine
University of Oxford（牛津大学）；Peking University（北京大学）；Yale University（耶鲁大学）；Tencent（腾讯）；Oxford-Suzhou Centre for Advanced Research（牛津-苏州高等研究院）；Shanghai Jiao Tong University School of Medicine（上海交通大学医学院）
Position, Not Provenance: Separating Reasoning Mediation from Sycophancy in Medical Vision-Language Models
IEM Kolkata（印度工程管理学院 Kolkata校区）；School of UEMK Kolkata（UEMK Kolkata学院）；Heritage Institute of Technology Kolkata（加尔各答遗产技术学院）；Indian Institute of Information Technology, Kalyani（卡利亚尼印度信息技术学院）
Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations
Faculty of CSE, Ho Chi Minh City University of Technology (HCMUT), VNUHCM（胡志明市理工大学计算机科学与工程学院，越南国家大学胡志明市分校）；Dept. of AI, FPT University（FPT大学人工智能系）；Faculty of DSAI, College of Technology, National Economic University（国民经济大学技术学院数据科学与人工智能系）；Dept. of AI Convergence, Chonnam National University（全南大学人工智能融合系）
Faithful, Interpretable Chest X-ray Diagnosis with Artifact-free B-cos Networks
Data and Web Science Group, University of Mannheim（曼海姆大学数据与网络科学组）；Max-Planck-Institute for Informatics, Saarland Informatics Campus（马克斯·普朗克研究所信息学研究所，萨尔兰州信息学校园）
针对 B-cos 网络在胸部 X 光诊断解释中存在混叠伪影的问题，本文引入 FLCPooling 与 BlurPool 抗锯齿策略，在保持预测性能的同时生成适合临床使用的无伪影忠实解释。
Hierarchical Variable Importance with Statistical Control for Medical Data-Based Prediction
Roche Pharma Research \& Early Development, F. Hoffmann-La Roche Ltd, Basel, Switzerland Université Paris-Saclay, Inria, CEA, Paris, Palaiseau, France Correspondance
