What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play
This work addresses the understudied issue of rigorously vetting interpretability for ethical AI applications, particularly in natural language processing, by providing a grounded evaluation with real human users.
The paper tackled the problem of evaluating machine learning interpretability in real-world human-AI cooperative tasks, finding that certain interpretations improved human performance in a Quizbowl question answering game, with novices benefiting more than experts.
Machine learning is an important tool for decision making, but its ethical and responsible application requires rigorous vetting of its interpretability and utility: an understudied problem, particularly for natural language processing models. We propose an evaluation of interpretation on a real task with real human users, where the effectiveness of interpretation is measured by how much it improves human performance. We design a grounded, realistic human-computer cooperative setting using a question answering task, Quizbowl. We recruit both trivia experts and novices to play this game with computer as their teammate, who communicates its prediction via three different interpretations. We also provide design guidance for natural language processing human-in-the-loop settings.