`

Timezone: »

 
Loopholes: a Window into Value Alignment and the Learning of Meaning
Sophie Bridgers · Elena Glassman · Laura Schulz · Tomer Ullman

Mon Dec 13 11:00 AM -- 11:10 AM (PST) @ None
Event URL: https://openreview.net/forum?id=pL4lmbI3ZZZ »

Exploiting a loophole, taking advantage of the ambiguity of language to do what someone says but not what they want, is a familiar facet of fable, law, and everyday life. Engaging with loopholes requires a nuanced understanding of goals, social ambiguity, and value alignment. Scientifically, the development of loopholes can help us better understand human communication, and design better human-AI interactions. However, cognitive research on this behavior remains scarce. A survey of parents reveals that loophole behavior is prevalent, frequent, and diverse in daily parent-child interactions, emerging around ages five to six. A further experiment shows that adults consider loophole behavior as less costly than non-compliance, and children increasingly differentiate loophole behavior from non-compliance from ages four to ten. We discuss the implications and limitations of the current work, together with a proposal for a formal framework for loophole behavior.

Author Information

Sophie Bridgers (Massachusetts Institute of Technology)
Elena Glassman (Harvard University)

I design, build and evaluate systems for comprehending and interacting with population-level structure and trends in large code and data corpora. I am an Assistant Professor of Computer Science at the Harvard Paulson School of Engineering & Applied Sciences and the Stanley A. Marks & William H. Marks Professor at the Radcliffe Institute for Advanced Study, specializing in human-computer interaction. At MIT, I earned a PhD and MEng in Electrical Engineering and Computer Science and a BS in Electrical Science and Engineering. Before joining Harvard, I was a postdoctoral scholar in Electrical Engineering and Computer Science at the University of California, Berkeley, where I received the Berkeley Institute for Data Science Moore/Sloan Data Science Fellowship.

Laura Schulz (MIT)

Laura Schulz received her BA in philosophy from the University of Michigan and her PhD in developmental psychology from the University of California, Berkeley. Her research focuses on the processes that support exploration, inquiry, and discovery in early childhood. She has contributed to topics including causal reasoning, social cognition, emotion understanding, moral reasoning, and the connection between play and learning. She has been honored with the American Psychological Association Distinguished Scientific Award for Early Career Contribution to Psychology; the National Academy of Sciences Troland Award; the Society for Research in Child Development Award for Early Career Research Contributions, and the NSF Presidential Early Career Award for Scientists and Engineers. She has been recognized as an MIT Macvicar Faculty Fellow for her contributions to undergraduate education and currently serves as the MIT Brain and Cognitive Sciences Associate Department Head for Diversity, Equity, Inclusion, and Justice.

Tomer Ullman (Harvard)

More from the Same Authors