Evaluating the performance of general purpose large language models in identifying human facial emotions
Benjamin W Nelson1,2, Ari Winbush3, Steven Siddals4
1Division of Digital Psychiatry, Department of Psychiatry, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA. bnelson9@bidmc.harvard.edu.
Abstract:
We evaluated the ability of three leading LLMs (GPT-4o, Gemini 2.0 Experimental, and Claude 3.5 Sonnet) to recognize human facial expression using the NimStim dataset. GPT and Gemini matched or exceeded human performance, especially for calm/neutral and surprise. All models showed strong agreement with ground truth, though fear was often misclassified. Findings underscore the growing socioemotional competence of LLMs and their potential for healthcare applications.
More Related Videos
Related Concept Videos
Facial Feedback Hypothesis
Labeling Emotion
Emotional Expression
Universal Facial Expressions
Psychologist Paul Ekman identified seven basic...
Muscles for Facial Expressions
Physiology of Emotion
Autonomic Nervous System
The autonomic nervous system (ANS) plays a critical role in emotional responses by regulating involuntary physiological functions. It consists of two main components: the sympathetic and parasympathetic systems. The sympathetic system...
Non-Verbal Cues


