Building Intelligent User Interfaces for Human-AI Alignment

TL;DR

This paper emphasizes the critical role of user interfaces in human-AI alignment, proposing a systematic framework and demonstrating how UI design can enhance alignment through case studies and initial experiments.

Contribution

It introduces a reference model and taxonomy for analyzing UI contributions to human-AI alignment, addressing a gap in existing research.

Findings

UI design can significantly impact human-AI alignment

The reference model helps identify UI improvement opportunities

Preliminary experiments show promising UI effects on alignment

Abstract

Aligning AI systems with human values fundamentally relies on effective human feedback. While significant research has addressed training algorithms, the role of user interface is often overlooked and only treated as an implementation detail rather than a critical factor of alignment. This paper addresses this gap by introducing a reference model that offers a systematic framework for analyzing where and how user interface contributions can improve human-AI alignment. The structured taxonomy of the reference model is demonstrated through two case studies and a preliminary investigation featuring six user interfaces. This work highlights opportunities to advance alignment through human-computer interaction.