Item

Abstract

Automated decision support systems promise to help human experts solve tasks
more efficiently and accurately. However, existing systems typically require
experts to understand when to cede agency to the system or when to exercise
their own agency. Moreover, if the experts develop a misplaced trust in the
system, their performance may worsen. In this work, we lift the above
requirement and develop automated decision support systems that, by design, do
not require experts to understand when to trust them to provably improve their
performance. To this end, we focus on multiclass classification tasks and
consider an automated decision support system that, for each data sample, uses
a classifier to recommend a subset of labels to a human expert. We first show
that, by looking at the design of such a system from the perspective of
conformal prediction, we can ensure that the probability that the recommended
subset of labels contains the true label matches almost exactly a target
probability value. Then, we develop an efficient and near-optimal search method
to find the target probability value under which the expert benefits the most
from using our system. Experiments on synthetic and real data demonstrate that
our system can help the experts make more accurate predictions and is robust to
the accuracy of the classifier it relies on.