AICYLGNov 16, 2024

Pluralistic Alignment Over Time

arXiv:2411.10654v15 citationsh-index: 60
Originality Synthesis-oriented
AI Analysis

This is an incremental position paper addressing alignment for groups with conflicting preferences in temporal decision-making.

The paper tackles the problem of evaluating AI alignment with multiple stakeholders over time, proposing temporal pluralism as a new approach to reflect conflicting values dynamically.

If an AI system makes decisions over time, how should we evaluate how aligned it is with a group of stakeholders (who may have conflicting values and preferences)? In this position paper, we advocate for consideration of temporal aspects including stakeholders' changing levels of satisfaction and their possibly temporally extended preferences. We suggest how a recent approach to evaluating fairness over time could be applied to a new form of pluralistic alignment: temporal pluralism, where the AI system reflects different stakeholders' values at different times.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes