99 citations · 238 across the 31 of their papers we have counts for
6 papers · 1 filter
Human-Like Geometric Abstraction in Large Pre-trained Neural Networks
Declan Campbell, Sreejan Kumar, Tyler Giallanza +2
Humans possess a remarkable capacity to recognize and manipulate abstract structure, which is especially apparent in the domain of geometry. Recent research in cognitive science su…
Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction
Sreejan Kumar, Raja Marjieh, Byron Zhang +5
Humans extract useful abstractions of the world from noisy sensory data. Serial reproduction allows us to study how people construe the world through a paradigm similar to the game…
Recovering Mental Representations from Large Language Models with Markov Chain Monte Carlo
Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths
Simulating sampling algorithms with people has proven a useful method for efficiently probing and understanding their mental representations. We propose that the same methods can b…
Improving Interpersonal Communication by Simulating Audiences with Language Models
Ryan Liu, Howard Yen, Raja Marjieh +2
How do we communicate with others to achieve our goals? We use our prior experience or advice from others, or construct a candidate utterance by predicting how it will be received.…
Concept Alignment as a Prerequisite for Value Alignment
Sunayana Rane, Mark Ho, Ilia Sucholutsky +1
Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends o…
Superhuman Artificial Intelligence Can Improve Human Decision Making by Increasing Novelty
Minkyu Shin, Jin Kim, Bas van Opheusden +1
How will superhuman artificial intelligence (AI) affect human decision making? And what will be the mechanisms behind this effect? We address these questions in a domain where AI a…