We study active learning where the labeler can not only return incorrect labels but also abstain from labeling. We consider different noise and abstention conditions of the labeler. We propose an algorithm which utilizes abstention responses, and analyze its statistical consistency and query complexity under fairly natural assumptions on the noise and abstention rate of the labeler. This algorithm is adaptive in a sense that it can automatically request less queries with a more informed or less noisy labeler. We couple our algorithm with lower bounds to show that under some technical conditions, it achieves nearly optimal query complexity.

We propose an algorithm which utilizes abstention responses, and analyze its statistical consistency and query complexity under fairly natural assumptions on the noise and abstention rate of the labeler.

We consider the problem of learning a multi-class classifier from labels as well as simple explanations that we call discriminative features .

We consider the problem of learning a multi-class classifier from labels as well as simple explanations that we call discriminative features .

In other words, these models are not aligned with their users.

To this end, we study the challenges of scalable oversight in the context of goal-conditioned hierarchical reinforcement learning.

As language models become more powerful, training and evaluation are increasingly bottlenecked by the data and metrics used for a particular task.