Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction
Track: long paper (up to 9 pages)
Keywords: serial reproduction, Bayesian inference, multimodal models, GPT-4, vision, language
TL;DR: We adapted a classic paradigm in cognitive psychology, serial reproduction, to study visuo-linguistic representations in humans vs large language model in order to show significant differences in how they build abstractions across modalities.
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.
Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.
Submission Number: 38
Loading