TALK    [MERL Seminar Series 2024] Tom Griffiths presents talk titled Tools from cognitive science to understand the behavior of large language models

Date & Time:

Wednesday, September 18, 2024; 1:00 PM

Abstract:

Large language models have been found to have surprising capabilities, even what have been called “sparks of artificial general intelligence.” However, understanding these models involves some significant challenges: their internal structure is extremely complicated, their training data is often opaque, and getting access to the underlying mechanisms is becoming increasingly difficult. As a consequence, researchers often have to resort to studying these systems based on their behavior. This situation is, of course, one that cognitive scientists are very familiar with — human brains are complicated systems trained on opaque data and typically difficult to study mechanistically. In this talk I will summarize some of the tools of cognitive science that are useful for understanding the behavior of large language models. Specifically, I will talk about how thinking about different levels of analysis (and Bayesian inference) can help us understand some behaviors that don’t seem particularly intelligent, how tasks like similarity judgment can be used to probe internal representations, how axiom violations can reveal interesting mechanisms, and how associations can reveal biases in systems that have been trained to be unbiased.

Speaker:

Tom Griffiths
Princeton University

Tom Griffiths is the Henry R. Luce Professor of Information Technology, Consciousness and Culture in the Departments of Psychology and Computer Science at Princeton University. His research explores connections between human and machine learning, using ideas from statistics and artificial intelligence to understand how people solve the challenging computational problems they encounter in everyday life. Tom completed his PhD in Psychology at Stanford University in 2005, and taught at Brown University and the University of California, Berkeley before moving to Princeton. He has received awards for his research from organizations ranging from the American Psychological Association to the National Academy of Sciences and is a co-author of the book Algorithms to Live By, introducing ideas from computer science and cognitive science to a general audience.

MERL Host:

Mouhacine Benosman

Research Areas:

Artificial Intelligence, Data Analytics, Machine Learning, Human-Computer Interaction