It Takes Two to Tango: Towards Theory of AI's Mind

By Arjun Chandrasekaran, Deshraj Yadav, Prithvijit Chattopadhyay, Viraj Prabhu, Devi Parikh. 2017

58 citations recorded by the source corpus.

Theory of Mind is the ability to attribute mental states (beliefs, intents, knowledge, perspectives, etc.) to others and recognize that these mental states may differ from one's own. Theory of Mind is critical to effective communication and to teams demonstrating higher collective performance. To effectively leverage the progress in Artificial Intelligence (AI) to make our lives more productive, it is important for humans and AI to work well together in a team. Traditionally, there has been much emphasis on research to make AI more accurate, and (to a lesser extent) on having it better understand human intentions, tendencies, beliefs, and contexts. The latter involves making AI more human-like and having it develop a theory of our minds. In this work, we argue that for human-AI teams to be effective, humans must also develop a theory of AI's mind (ToAIM) - get to know its strengths, weaknesses, beliefs, and quirks. We instantiate these ideas within the domain of Visual Question Answering (VQA). We find that using just a few examples (50), lay people can be trained to better predict responses and oncoming failures of a complex VQA model. We further evaluate the role existing explanation (or interpretability) modalities play in helping humans build ToAIM. Explainable AI has received considerable scientific and popular attention in recent times. Surprisingly, we find that having access to the model's internal states - its confidence in its top-k predictions, explicit or implicit attention maps which highlight regions in the image (and words in the question) the model is looking at (and listening to) while answering a question about an image - do not help people better predict its behavior.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Cognitive Science & Psychology, Philosophy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Cognitive Science & Psychology

In Philosophy

Citations in the corpus

Evaluating Theory of Mind in Question Answering (2018, background): “Finally, Chandrasekaran et al. (2017) take a dif-2 ferent approach by studying whether people can understand the “beliefs” of a visual-question answering system.”
What is AI Literacy? Competencies and Design Considerations (2020, background): “Users likely do not need to understand all of these strategies in detail, but a high-level understanding of how computers make decisions can aid in interpreting and understanding algorithms [29] (Competency 8 (Decision-Making)).”
MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks (2021, background): “As a first step to address this question, this paper explores theory of mind modeling (Chandrasekaran et al., 2017; Rabinowitz et al., 2018; Jara-Ettinger, 2019) in situated language communication (Iwahashi et al.”
Evaluating Explanations by Cognitive Value (2018, unknown): “However, such explanations are not useful to an end-user in either understanding the AI’s decision or in debugging the model [14].”
Evaluating Visual Conversational Agents via Cooperative Human-AI Games (2017, background): “Recently, (Chandrasekaran et al. 2017) showed that human subjects can predict the responses of an AI more accurately with higher familiarity with the AI.”