Neural Synchrony Between Socially Interacting Language Models

2026-02-19

AI Summary

This study investigates whether large language models (LLMs) exhibit human-like “social cognition” during social interactions, focusing on whether neural synchrony—a phenomenon observed in human brains during shared understanding—emerges in their internal representations. To this end, we construct a multi-agent social simulation environment and introduce the concept of neural synchrony into LLM research for the first time. By analyzing temporally aligned hidden-layer representations, measuring representational similarity, and evaluating performance on social tasks, we propose representational synchrony as a novel metric for assessing model sociality. Our experiments demonstrate that LLMs indeed exhibit significant representational synchrony during interaction, and this synchrony strongly correlates with their performance on social tasks, offering a new perspective for understanding and evaluating the social capabilities of artificial intelligence.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Neuroscience has uncovered a fundamental mechanism of our social nature: human brain activity becomes synchronized with others in many social contexts involving interaction. Traditionally, social minds have been regarded as an exclusive property of living beings. Although large language models (LLMs) are widely accepted as powerful approximations of human behavior, with multi-LLM system being extensively explored to enhance their capabilities, it remains controversial whether they can be meaningfully compared to human social minds. In this work, we explore neural synchrony between socially interacting LLMs as an empirical evidence for this debate. Specifically, we introduce neural synchrony during social simulations as a novel proxy for analyzing the sociality of LLMs at the representational level. Through carefully designed experiments, we demonstrate that it reliably reflects both social engagement and temporal alignment in their interactions. Our findings indicate that neural synchrony between LLMs is strongly correlated with their social performance, highlighting an important link between neural synchrony and the social behaviors of LLMs. Our work offers a new perspective to examine the"social minds"of LLMs, highlighting surprising parallels in the internal dynamics that underlie human and LLM social interaction.

Problem

• neural synchrony
• large language models
• social interaction
• social minds
• representational alignment

Innovation

• neural synchrony
• large language models
• social interaction
• representational alignment
• multi-agent systems