Harnessing Explanations to Bridge AI and Humans
This work tackles the challenge of making AI explanations effective for human users in high-stakes domains, but it is incremental as it focuses on identifying gaps rather than presenting a novel solution.
The paper addresses the problem that explanations from AI models often fail to improve human decision-making in critical applications like recidivism prediction and medical diagnosis, proposing future directions to bridge this gap without specifying concrete results or numbers.
Machine learning models are increasingly integrated into societally critical applications such as recidivism prediction and medical diagnosis, thanks to their superior predictive power. In these applications, however, full automation is often not desired due to ethical and legal concerns. The research community has thus ventured into developing interpretable methods that explain machine predictions. While these explanations are meant to assist humans in understanding machine predictions and thereby allowing humans to make better decisions, this hypothesis is not supported in many recent studies. To improve human decision-making with AI assistance, we propose future directions for closing the gap between the efficacy of explanations and improvement in human performance.