Uploaded June 2022 | Updated November 2026, 1 day ago
Abstract: Humans are increasingly working with AI-powered algorithms, sharing the road with autonomous vehicles, sharing hospital wards with autonomous surgery robots, and making joint decisions with autonomous algorithms. As we adapt to the increasing presence of AIs playing significant roles in our organizations and society, it is important to understand how people respond and think about AIs decision-making. In my talk I will discuss two questions regarding human responses to AI decision-making, focusing on the moral domain. The first is: Do people want AIs to make moral decisions? I find that people want moral decision-makers to have the ability to think but also to feel, and since robots are perceived as being unable to feel, people do not want them to make moral decisions. I also find that when human decision-making is associated with unequal outcomes, such as racial and SES health disparities, people are more willing to accept AIs as decision-makers. The second is: When AIs would have to make moral decisions, such as in the case of self-driving cars, how do people want them to do that? I show that, in contrast to other published work, people want AIs not to discriminate between humans according to age, gender, and social status.
Bio: Kurt Gray is an Associate Professor of Psychology and Neuroscience at the University of North Carolina. He is also the Director of the Center for the Science of Moral Understanding, which is catalyzing a new field of scientific inquiry focused on identifying data-driven ways of reducing societal intolerance. Gray received his Ph.D. in Social Psychology from Harvard University, and is an expert in moral psychology and social cognition, with over 80 scientific publications. He is an award-winning researcher, educator, and author of the mass market book “The Mind Club: Who Thinks, What Feels, and Why It Matter” (Viking). Gray has been funded by the Charles Koch Foundation, the National Science Foundation, and the John Templeton Foundation. His work has been covered in the New York Times, The Economist, The Wall Street Journal, Science Magazine, Wired, Slate, and The New Yorker.
Abstract: Humans are increasingly working with AI-powered algorithms, sharing the road with autonomous vehicles, sharing hospital wards with autonomous surgery robots, and making joint decisions with autonomous algorithms. As we adapt to the increasing presence of AIs playing significant roles in our organizations and society, it is important to understand how people respond and think about AIs decision-making. In my talk I will discuss two questions regarding human responses to AI decision-making, focusing on the moral domain. The first is: Do people want AIs to make moral decisions? I find that people want moral decision-makers to have the ability to think but also to feel, and since robots are perceived as being unable to feel, people do not want them to make moral decisions. I also find that when human decision-making is associated with unequal outcomes, such as racial and SES health disparities, people are more willing to accept AIs as decision-makers. The second is: When AIs would have to make moral decisions, such as in the case of self-driving cars, how do people want them to do that? I show that, in contrast to other published work, people want AIs not to discriminate between humans according to age, gender, and social status.
Bio: Kurt Gray is an Associate Professor of Psychology and Neuroscience at the University of North Carolina. He is also the Director of the Center for the Science of Moral Understanding, which is catalyzing a new field of scientific inquiry focused on identifying data-driven ways of reducing societal intolerance. Gray received his Ph.D. in Social Psychology from Harvard University, and is an expert in moral psychology and social cognition, with over 80 scientific publications. He is an award-winning researcher, educator, and author of the mass market book “The Mind Club: Who Thinks, What Feels, and Why It Matter” (Viking). Gray has been funded by the Charles Koch Foundation, the National Science Foundation, and the John Templeton Foundation. His work has been covered in the New York Times, The Economist, The Wall Street Journal, Science Magazine, Wired, Slate, and The New Yorker.










![Explaining Answers with Entailment Trees
Explaining Answers with Entailment Trees
Bhavana Dalvi
https://allenai.org/team/bhavanad
Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a rationale). If this could be done, new opportunities for understanding and debugging the systems reasoning become possible. Our approach is to generate explanations in the form of entailment trees, namely a tree of multipremise entailment steps from facts that are known, through intermediate conclusions, to the hypothesis of interest (namely the question + answer). To train a model with this skill, we created ENTAILMENTBANK, the first dataset to contain multistep entailment trees. Given a hypothesis (question + answer), we define three increasingly difficult explanation tasks: generate a valid entailment tree given (a) all relevant sentences (b) all relevant and some irrelevant sentences, or (c) a corpus. We show that a strong language model can partially solve these tasks, in particular when the relevant sentences are included in the input (e.g., 35% of trees for (a) are perfect), and with indications of generalization to other domains. This work is significant as it provides a new type of dataset (multistep entailments) and baselines, offering a new avenue for the community to generate richer, more systematic explanations. [ Paper published in EMNLP 2021, https://arxiv.org/abs/2104.08661 ] Explaining Answers with Entailment Trees](https://i.ytimg.com/vi/QPSZQYA1RmA/mqdefault.jpg)