Statistical attribute alignment for black-box generative AI via output post-processing
Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure that the distribution of an attribute of an AI-generated output aligns with a user-specified target. This is motivated by examples such as fairness, where we want to ensure that a protected attribute (e.g., gender, race, or age categories) follows a…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
