Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibration
This work addresses the challenge of enhancing decision-making in human-AI collaboration for classification, though it is incremental as it builds on existing combination methods.
The paper tackles the problem of combining human and model predictions for classification tasks to improve accuracy, showing that their method consistently outperforms either human or model alone on CIFAR-10 and ImageNet datasets, with parameters estimable from as few as ten labeled data points.
An increasingly common use case for machine learning models is augmenting the abilities of human decision makers. For classification tasks where neither the human or model are perfectly accurate, a key step in obtaining high performance is combining their individual predictions in a manner that leverages their relative strengths. In this work, we develop a set of algorithms that combine the probabilistic output of a model with the class-level output of a human. We show theoretically that the accuracy of our combination model is driven not only by the individual human and model accuracies, but also by the model's confidence. Empirical results on image classification with CIFAR-10 and a subset of ImageNet demonstrate that such human-model combinations consistently have higher accuracies than the model or human alone, and that the parameters of the combination method can be estimated effectively with as few as ten labeled datapoints.