"Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans
This work addresses the challenge of enhancing human-AI synergy in decision-making by developing tutorials for training phases, though it is incremental as it builds on existing explanation methods.
The paper tackled the problem of helping humans understand unsalient or counterintuitive patterns in machine learning models by introducing model-driven tutorials during training, and found that tutorials improved human performance in deceptive review detection, with simple models being more useful than deep learning despite lower predictive accuracy.
To support human decision making with machine learning models, we often need to elucidate patterns embedded in the models that are unsalient, unknown, or counterintuitive to humans. While existing approaches focus on explaining machine predictions with real-time assistance, we explore model-driven tutorials to help humans understand these patterns in a training phase. We consider both tutorials with guidelines from scientific papers, analogous to current practices of science communication, and automatically selected examples from training data with explanations. We use deceptive review detection as a testbed and conduct large-scale, randomized human-subject experiments to examine the effectiveness of such tutorials. We find that tutorials indeed improve human performance, with and without real-time assistance. In particular, although deep learning provides superior predictive performance than simple models, tutorials and explanations from simple models are more useful to humans. Our work suggests future directions for human-centered tutorials and explanations towards a synergy between humans and AI.