返回首页
arXiv AI··论文与技术

Whose Ground Truth? Embracing Ambiguity in Human-Centered AI

中文摘要

该研究主张以人为本的AI应拥抱歧义,挑战单一真值的传统假设,重视人类多元解释。

English Summary

This research argues that human-centered AI should embrace ambiguity and diverse interpretations instead of assuming a single ground truth, challenging conventional machine learning paradigms.

原文节选

arXiv:2610.10805v1 Announce Type: new Abstract: 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.