Saved in:
Bibliographic Details
Main Authors: Strachan, James W. A., Pansardi, Oriana, Scaliti, Eugenio, Celotto, Marco, Saxena, Krati, Yi, Chunzhi, Manzi, Fabio, Rufo, Alessandro, Manzi, Guido, Graziano, Michael S. A., Panzeri, Stefano, Becchio, Cristina
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.22309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929568407879680
author Strachan, James W. A.
Pansardi, Oriana
Scaliti, Eugenio
Celotto, Marco
Saxena, Krati
Yi, Chunzhi
Manzi, Fabio
Rufo, Alessandro
Manzi, Guido
Graziano, Michael S. A.
Panzeri, Stefano
Becchio, Cristina
author_facet Strachan, James W. A.
Pansardi, Oriana
Scaliti, Eugenio
Celotto, Marco
Saxena, Krati
Yi, Chunzhi
Manzi, Fabio
Rufo, Alessandro
Manzi, Guido
Graziano, Michael S. A.
Panzeri, Stefano
Becchio, Cristina
contents Large Language Models (LLMs) are capable of reproducing human-like inferences, including inferences about emotions and mental states, from text. Whether this capability extends beyond text to other modalities remains unclear. Humans possess a sophisticated ability to read the mind in the eyes of other people. Here we tested whether this ability is also present in GPT-4o, a multimodal LLM. Using two versions of a widely used theory of mind test, the Reading the Mind in Eyes Test and the Multiracial Reading the Mind in the Eyes Test, we found that GPT-4o outperformed humans in interpreting mental states from upright faces but underperformed humans when faces were inverted. While humans in our sample showed no difference between White and Non-white faces, GPT-4o's accuracy was higher for White than for Non-white faces. GPT-4o's errors were not random but revealed a highly consistent, yet incorrect, processing of mental-state information across trials, with an orientation-dependent error structure that qualitatively differed from that of humans for inverted faces but not for upright faces. These findings highlight how advanced mental state inference abilities and human-like face processing signatures, such as inversion effects, coexist in GPT-4o alongside substantial differences in information processing compared to humans.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22309
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GPT-4o reads the mind in the eyes
Strachan, James W. A.
Pansardi, Oriana
Scaliti, Eugenio
Celotto, Marco
Saxena, Krati
Yi, Chunzhi
Manzi, Fabio
Rufo, Alessandro
Manzi, Guido
Graziano, Michael S. A.
Panzeri, Stefano
Becchio, Cristina
Human-Computer Interaction
Computers and Society
Large Language Models (LLMs) are capable of reproducing human-like inferences, including inferences about emotions and mental states, from text. Whether this capability extends beyond text to other modalities remains unclear. Humans possess a sophisticated ability to read the mind in the eyes of other people. Here we tested whether this ability is also present in GPT-4o, a multimodal LLM. Using two versions of a widely used theory of mind test, the Reading the Mind in Eyes Test and the Multiracial Reading the Mind in the Eyes Test, we found that GPT-4o outperformed humans in interpreting mental states from upright faces but underperformed humans when faces were inverted. While humans in our sample showed no difference between White and Non-white faces, GPT-4o's accuracy was higher for White than for Non-white faces. GPT-4o's errors were not random but revealed a highly consistent, yet incorrect, processing of mental-state information across trials, with an orientation-dependent error structure that qualitatively differed from that of humans for inverted faces but not for upright faces. These findings highlight how advanced mental state inference abilities and human-like face processing signatures, such as inversion effects, coexist in GPT-4o alongside substantial differences in information processing compared to humans.
title GPT-4o reads the mind in the eyes
topic Human-Computer Interaction
Computers and Society
url https://arxiv.org/abs/2410.22309