Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction

Author:

Sreejan Kumar, Raja Marjieh, Byron Zhang, Declan Campbell, Michael Y. Hu, Umang Bhatt, Brenden Lake, Thomas L. Griffiths

Keyword:

Computer Science, Artificial Intelligence, Artificial Intelligence (cs.AI), Computation and Language (cs.CL), Neurons and Cognition (q-bio.NC)

journal:

date:

2024-02-06 00:00:00

Abstract

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 of telephone, where one person observes a stimulus and reproduces it for the next to form a chain of reproductions. Past serial reproduction experiments typically employ a single sensory modality, but humans often communicate abstractions of the world to each other through language. To investigate the effect language on the formation of abstractions, we implement a novel multimodal serial reproduction framework by asking people who receive a visual stimulus to reproduce it in a linguistic format, and vice versa. We ran unimodal and multimodal chains with both humans and GPT-4 and find that adding language as a modality has a larger effect on human reproductions than GPT-4's. This suggests human visual and linguistic representations are more dissociable than those of GPT-4.

PDF: Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction.pdf