发表机构
Hasso Plattner Institute; LMU Munich; MIT; Aalto University; ELLIS Institute Finland(哈索·普拉特纳研究所; 慕尼黑大学; 麻省理工学院; 阿尔托大学; 芬兰ELLIS研究所)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
针对价值对齐缺乏测量工具的问题,构建并验证了一个13条目心理测量量表,涵盖价值理解与价值体现两个维度,并开发了6条目简版,为HCI研究提供可靠评估指标。
AI 中文摘要
价值对齐是人工智能和人机交互研究的核心目标,然而目前尚无经过验证的测量工具来评估用户对价值对齐的感知。这一空白阻碍了研究结果的比较与积累,并限制了相关应用的有效性,而在这些应用中,理解用户观点至关重要。我们构建并评估了一个包含13个条目的心理测量量表,该量表从两个维度测量感知到的价值对齐:价值理解与价值体现。该量表基于从先前实证研究中提取的大型条目池,经专家筛选,最终由来自不同人工智能场景的用户(N=607)进行评估。对独立样本(N=259)进行的验证性因子分析确认了双因子结构,且两个子量表均具有较高的内部一致性。通过优化,我们还开发了一个包含6个条目的简短版本,以便快速施测。该量表是一种可靠的测量工具,为人机交互研究者提供了一个跨情境的通用评估指标。
英文摘要
Value alignment is a central objective in AI and HCI research, yet no validated instrument measures how users perceive it. This gap hampers the comparison and accumulation of findings and limits the effectiveness of applications, where understanding users' viewpoints is critical. We construct and evaluate a 13-item psychometric scale that measures perceived value alignment across two components: value understanding and value manifestation. It is based on a large item pool drawn from prior empirical studies, filtered by experts, and finally assessed by users (N=607) across diverse AI scenarios. Confirmatory factor analysis on an independent sample (N=259) confirmed the two-factor structure and high internal consistency for both subscales. Using optimization, we also derived a 6-item short form for quick administration. The scale is a reliable measure, providing HCI researchers with a common evaluation metric across contexts.