Abstract
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.
Abstract (translated)
心理理论是将心理状态（信仰，意图，知识，观点等）归因于他人的能力，并认识到这些心理状态可能与自己的不同。心理理论对于有效的沟通和团队表现出更高的集体表现至关重要。为了有效地利用人工智能（AI）中的进步来提高我们的生活效率，对于人类和AI来说，在团队中一起工作非常重要。传统上，人们一直非常重视研究，以使AI更加准确，并且（在较小程度上）更好地理解人的意图，倾向，信仰和背景。后者涉及让人工智能更像人类，让它发展出我们的头脑理论。在这项工作中，我们认为人类AI团队要有效，人类还必须发展AI的理论（ToAIM） - 了解其优势，弱点，信仰和怪癖。我们在Visual Question Answering（VQA）的范畴内实例化这些想法。我们发现仅使用几个例子（50），就可以培训外行人员更好地预测复杂的VQA模型的响应和即将到来的故障。我们进一步评估现有解释（或可解释性）模式在帮助人类构建ToAIM方面的作用。可解释的AI近来已经受到了相当多的科学和普遍的关注。令人惊讶的是，我们发现可以访问模型的内部状态 - 对top-k预测的信心，显示或隐含关注地图，突出显示图像中的区域（以及问题中的单词）模型正在查看（并正在聆听）同时回答关于图像的问题 - 不会帮助人们更好地预测其行为。
URL
https://arxiv.org/abs/1704.00717
