The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
Liang, Ronan Le Bras, Katharina Reinecke, and Maarten Sap
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
An online experiment finds that showing users an overview of an AI's values reduces reliance on AI suggestions during writing tasks.
citing papers explorer
-
A Roadmap to Pluralistic Alignment
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
-
Framing an AI with Values Reduces AI Reliance in AI-supported Writing Tasks
An online experiment finds that showing users an overview of an AI's values reduces reliance on AI suggestions during writing tasks.