Invited Talk
in
Workshop: Workshop on Behavioral Machine Learning
Sendhil Mullainathan: Misunderstandings
Abstract:
In this talk I will document two kinds of misunderstanding: people misunderstanding algorithms; and algorithms misunderstanding people. The empirical work is done on LLMs and supervised learning. In both cases, I show how these misunderstandings are consequential; and have implications for how models should be trained differently.
Chat is not available.