Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| 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 |