The Emotional Alignment Design Policy

TL;DR

The paper proposes the Emotional Alignment Design Policy, guiding artificial systems to evoke appropriate emotional responses based on their capacities and moral status, addressing ethical and practical challenges.

Contribution

It introduces the concept of emotional alignment in AI design and discusses the ethical, practical, and philosophical challenges involved.

Findings

Identifies potential violations of emotional alignment principles.

Highlights challenges in respecting user autonomy and moral considerations.

Discusses navigating disagreement and uncertainty in design choices.

Abstract

According to what we call the Emotional Alignment Design Policy, artificial entities should be designed to elicit emotional reactions from users that appropriately reflect the entities' capacities and moral status, or lack thereof. This principle can be violated in two ways: by designing an artificial system that elicits stronger or weaker emotional reactions than its capacities and moral status warrant (overshooting or undershooting), or by designing a system that elicits the wrong type of emotional reaction (hitting the wrong target). Although presumably attractive, practical implementation faces several challenges including: How can we respect user autonomy while promoting appropriate responses? How should we navigate expert and public disagreement and uncertainty about facts and values? What if emotional alignment seems to require creating or destroying entities with moral status? To what extent should designs conform to versus attempt to alter user assumptions and attitudes?