Standoff: benchmarking representation learning for nonverbal theory of mind tasks

Joel Phillips Michelson, Deepayan Sanyal, James Ainooson, Effat Farhana, Maithilee Kunda

Abstract:

We present our design and implementation of Standoff, an innovative benchmark suite of computational theory of
mind tasks, based on the competitive feeding paradigm from comparative psychology. We find that a small convolutional LSTM
model without explicit theory of mind mechanisms can reach
high levels of accuracy when exposed to the full variety of our
task design during training. Such a model faces generalization
challenges when exposed to narrower subsets of tasks. Finally,
we discuss how this test may be used as a gateway for studying
theory of mind skills beyond attribution of seeing and knowing.