发表机构
Massachusetts Institute of Technology; Novo Nordisk A/S; Copenhagen Business School; Aalborg University（麻省理工学院; 诺和诺德公司; 哥本哈根商学院; 奥尔堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该论文针对以人为中心AI中传统真实值假设忽略人类解释多样性的问题，提出应建模合理人类判断的解释空间，区分有意义歧义与标注噪声，以开发更贴合人类多样性的AI。
AI 中文摘要
随着AI系统越来越多地与人交互并对人做出决策，理解人类解释成为开发以人为中心的AI的重要部分。传统机器学习和AI系统大多基于存在单一确定真实值的假设开发，人类标注的变异性常通过聚合解决或被视为噪声。但对于许多以人为中心的任务，人类解释本质上是模糊的，同一输入的多种解释可能同时合理且有效。将此类歧义简化为单一目标，可能会忽略人类感知、判断和经验多样性的重要信息。在这篇立场论文中，我们呼吁转向对合理人类判断的解释空间进行建模，同时区分有意义的歧义与标注噪声。我们认为，这种视角应指导AI系统的表示、学习、评估、部署和治理，以支持更以人为中心的AI，更好地反映人类解释的多样性。
英文摘要
As AI systems increasingly interact with people and make decisions about them, understanding human interpretations becomes an important part of developing human-centered AI. Conventional machine learning and AI systems are largely developed under the assumption that a single definitive ground truth exists, with variability in human annotations often resolved through aggregation or treated as noise. However, for many human-centered tasks, human interpretation is inherently ambiguous, and multiple interpretations of the same input may be simultaneously reasonable and valid. Reducing such ambiguity to a single target risks overlooking meaningful information about the diversity of human perception, judgment, and experience. In this position paper, we call for a shift towards modeling the interpretation space of plausible human judgments, while distinguishing meaningful ambiguity from annotation noise. We argue that this perspective should guide how AI systems are represented, learned, evaluated, deployed, and governed, supporting more human-centered AI that better reflects the diversity of human interpretation.
CommentsAccepted to NeurIPS 2026 Trustworthy AI for Good Workshop
