标签
This position paper advocates computational argumentation as a formal foundation for Evaluative AI, which supports human decision-making by presenting competing hypotheses with evidence for and against, rather than single recommendations.
Introduces CANOE, a multi-agent neuro-symbolic framework for open-ended care plan coordination that uses argumentative computation and human-in-the-loop contestation to improve transparency, safety, and clinical correctness.
本文介绍了一个包含17k句子的语料库,该语料库对COVID-19期间三个德国政治领域的论证段落进行了标注,并开展了一项自动识别此类段落的试点研究,发现边界难以确定,且模型存在确认偏差。
本文提出一个框架,利用Toulmin论证模型对基于OCT图像的ML视网膜诊断进行结构化,整合生物标志物提取、医学大语言模型推理(MedGemma)和相似度度量(MedSigLip),以实现可解释且基于证据的诊断辅助。
本文介绍了一个范畴论框架,用于通过组合可复用的foundries(基础组件)来构建可验证、局部真值保持的基础模型,该框架在Odyssey系统中实现,并计划于ICML 2026进行教程讲解。