What are you optimizing for? Aligning Recommender Systems with Human Values
It addresses the problem of aligning AI systems with complex human values for users and stakeholders, though it is incremental in proposing new directions rather than presenting a novel method.
The paper examines how recommender systems can be aligned with human values like diversity and fairness, identifying current practices as piecemeal and proposing AI alignment approaches for direct stakeholder involvement.
We describe cases where real recommender systems were modified in the service of various human values such as diversity, fairness, well-being, time well spent, and factual accuracy. From this we identify the current practice of values engineering: the creation of classifiers from human-created data with value-based labels. This has worked in practice for a variety of issues, but problems are addressed one at a time, and users and other stakeholders have seldom been involved. Instead, we look to AI alignment work for approaches that could learn complex values directly from stakeholders, and identify four major directions: useful measures of alignment, participatory design and operation, interactive value learning, and informed deliberative judgments.