Emotional Intelligence of Large Language Models

by   Xuena Wang, et al.

Large Language Models (LLMs) have demonstrated remarkable abilities across numerous disciplines, primarily assessed through tasks in language generation, knowledge utilization, and complex reasoning. However, their alignment with human emotions and values, which is critical for real-world applications, has not been systematically evaluated. Here, we assessed LLMs' Emotional Intelligence (EI), encompassing emotion recognition, interpretation, and understanding, which is necessary for effective communication and social interactions. Specifically, we first developed a novel psychometric assessment focusing on Emotion Understanding (EU), a core component of EI, suitable for both humans and LLMs. This test requires evaluating complex emotions (e.g., surprised, joyful, puzzled, proud) in realistic scenarios (e.g., despite feeling underperformed, John surprisingly achieved a top score). With a reference frame constructed from over 500 adults, we tested a variety of mainstream LLMs. Most achieved above-average EQ scores, with GPT-4 exceeding 89 pattern analysis revealed that some LLMs apparently did not reply on the human-like mechanism to achieve human-level performance, as their representational patterns were qualitatively distinct from humans. In addition, we discussed the impact of factors such as model size, training method, and architecture on LLMs' EQ. In summary, our study presents one of the first psychometric evaluations of the human-like characteristics of LLMs, which may shed light on the future development of LLMs aiming for both high intellectual and emotional intelligence. Project website: https://emotional-intelligence.github.io/


page 1

page 2

page 3

page 4


Emotion Recognition based on Psychological Components in Guided Narratives for Emotion Regulation

Emotion regulation is a crucial element in dealing with emotional events...

Is GPT a Computational Model of Emotion? Detailed Analysis

This paper investigates the emotional reasoning abilities of the GPT fam...

Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench

Recently, the community has witnessed the advancement of Large Language ...

Emotional control - conditio sine qua non for advanced artificial intelligences?

Humans dispose of two intertwined information processing pathways, cogni...

Evaluating large language models' ability to understand metaphor and sarcasm using a screening test for Asperger syndrome

Metaphors and sarcasm are precious fruits of our highly-evolved social c...

Exploring ChatGPT's Empathic Abilities

Empathy is often understood as the ability to share and understand anoth...

Context-Dependent Models for Predicting and Characterizing Facial Expressiveness

In recent years, extensive research has emerged in affective computing o...

Please sign up or login with your details

Forgot password? Click here to reset