Academically intelligent LLMs are not necessarily socially intelligent

TL;DR

This study develops a standardized test to evaluate the social intelligence of large language models, revealing that their social skills are limited and distinct from their academic abilities, with social factors influencing their performance.

Contribution

The paper introduces SESI, a novel social intelligence assessment framework for LLMs, and provides extensive evaluation results highlighting the gap between academic and social intelligence.

Findings

LLMs show significant room for improvement in social intelligence.

Superficial friendliness is a primary source of errors.

Social intelligence in LLMs is influenced by social factors and is distinct from academic intelligence.

Abstract

The academic intelligence of large language models (LLMs) has made remarkable progress in recent times, but their social intelligence performance remains unclear. Inspired by established human social intelligence frameworks, particularly Daniel Goleman's social intelligence theory, we have developed a standardized social intelligence test based on real-world social scenarios to comprehensively assess the social intelligence of LLMs, termed as the Situational Evaluation of Social Intelligence (SESI). We conducted an extensive evaluation with 13 recent popular and state-of-art LLM agents on SESI. The results indicate the social intelligence of LLMs still has significant room for improvement, with superficially friendliness as a primary reason for errors. Moreover, there exists a relatively low correlation between the social intelligence and academic intelligence exhibited by LLMs, suggesting that social intelligence is distinct from academic intelligence for LLMs. Additionally, while it is observed that LLMs can't ``understand'' what social intelligence is, their social intelligence, similar to that of humans, is influenced by social factors.