A Scale For Value Alignment In Human-AI Interaction

2026-10-07

AI Summary

This study addresses the lack of validated measurement instruments for perceived value alignment in Human-Computer Interaction (HCI), which has constrained research comparability. To bridge this gap, we developed and validated a psychometric scale encompassing two dimensions: value comprehension and value expression. Employing the Delphi method, confirmatory factor analysis, and optimization algorithms, the instrument was refined through expert evaluation and cross-contextual testing with 607 users, yielding both a 13-item standard version and a 6-item short form. The two-factor structure and high internal consistency were confirmed in an independent sample. This work presents the first empirically validated scale for measuring perceived value alignment, filling a critical void in HCI research and providing a standardized, reliable tool for cross-situational assessment.

Abstract

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.

Problem

• Value Alignment
• Human-AI Interaction
• Psychometric Scale
• Perceived Value Alignment
• HCI

Innovation

• Value Alignment
• Psychometric Scale
• Human-AI Interaction
• Confirmatory Factor Analysis
• Scale Development