Reframing explanation as an interactive medium: The EQUAS (Explainable QUestion Answering System) project. Issue 4 (17th January 2022)

• Record Type: Journal Article
• Authors: Ferguson, William; Batra, Dhruv; Mooney, Raymond; Parikh, Devi; Torralba, Antonio; Bau, David; Diller, David; Fasching, Josh; Fiotto‐Kaufman, Jaden; Goyal, Yash; Miller, Jeff; Moffitt, Kerry; Montes de Oca, Alex; Selvaraju, Ramprasaath R.; Shrivastava, Ayush; Wu, Jialin; Lee, Stefan
• Other Names: Gunning Dave guestEditor.; Vorm Eric guestEditor.; Wang Jennifer Yunyan guestEditor.; Turek Matt guestEditor.
• Is Part Of: Applied AI Letters. Volume 2:Issue 4(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-01-17
• Subjects: explainable artificial intelligence (XAI) -- human/computer interaction (HCI) -- tasking and adapting agents -- visual question answering (VQA); 006.3
• DOI: 10.1002/ail2.60
• Languages: English
• ISSNs: 2689-5595

Abstract

Abstract: This letter is a retrospective analysis of our team's research for the Defense Advanced Research Projects Agency Explainable Artificial Intelligence project. Our initial approach was to use salience maps, English sentences, and lists of feature names to explain the behavior of deep‐learning‐based discriminative systems, with particular focus on visual question answering systems. We found that presenting static explanations along with answers led to limited positive effects. By exploring various combinations of machine and human explanation production and consumption, we evolved a notion of explanation as an interactive process that takes place usually between humans and artificial intelligence systems but sometimes within the software system. We realized that by interacting via explanations people could task and adapt machine learning (ML) agents. We added affordances for editing explanations and modified the ML system to act in accordance with the edits to produce an interpretable interface to the agent. Through this interface, editing an explanation can adapt a system's performance to new, modified purposes. This deep tasking, wherein the agent knows its objective and the explanation for that objective, will be critical to enable higher levels of autonomy. Abstract : Under the Explainable Artificial Intelligence Project, we demonstrated limited, positive effects on users from statically presenting explanations along with the system's answers—for example, when teaching people to identify bird species. We then illustrated how interacting via explanations could enable people to task and adapt machine learning (ML) systems. This deep tasking, wherein the agent knows its objective and the explanation for that objective, will be critical to enable higher levels of autonomy.