Humans learn too: Better Human-AI Interaction using Optimized Human Inputs
This work addresses the problem of inefficient human-AI interaction for users by enabling humans to learn and adapt their inputs, though it is incremental as it builds on existing optimization methods.
The paper tackles the problem of one-sided optimization in human-AI interaction by optimizing human inputs rather than AI models, resulting in lower error rates and reduced effort for humans while keeping changes to original inputs limited.
Humans rely more and more on systems with AI components. The AI community typically treats human inputs as a given and optimizes AI models only. This thinking is one-sided and it neglects the fact that humans can learn, too. In this work, human inputs are optimized for better interaction with an AI model while keeping the model fixed. The optimized inputs are accompanied by instructions on how to create them. They allow humans to save time and cut on errors, while keeping required changes to original inputs limited. We propose continuous and discrete optimization methods modifying samples in an iterative fashion. Our quantitative and qualitative evaluation including a human study on different hand-generated inputs shows that the generated proposals lead to lower error rates, require less effort to create and differ only modestly from the original samples.