The role of System 1 and System 2 semantic memory structure in human and LLM biases

2026-04-14

AI Summary

This study investigates the cognitive origins of implicit bias in both humans and large language models (LLMs), focusing on the differential roles of System 1 and System 2 thinking—as conceptualized by dual-process theory—in bias generation and regulation. By modeling these two modes of thought as distinct semantic memory network structures and analyzing comparable data generated by humans and LLMs through network science methods, the research examines their associations with gender-based implicit bias. Integrating dual-process theory with semantic memory networks for the first time, the study reveals that humans possess irreducible semantic structures—particularly those linked to System 2—that are significantly associated with lower levels of implicit bias. In contrast, LLMs lack such stable regulatory architectures, highlighting a fundamental divergence between human cognition and artificial systems in the organization of conceptual knowledge.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Natural Language Processing: (Large) Language Models
• Humans and AI: Learning Human Values and Preferences

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Implicit biases in both humans and large language models (LLMs) pose significant societal risks. Dual process theories propose that biases arise primarily from associative System 1 thinking, while deliberative System 2 thinking mitigates bias, but the cognitive mechanisms that give rise to this phenomenon remain poorly understood. To better understand what underlies this duality in humans, and possibly in LLMs, we model System 1 and System 2 thinking as semantic memory networks with distinct structures, built from comparable datasets generated by both humans and LLMs. We then investigate how these distinct semantic memory structures relate to implicit gender bias using network-based evaluation metrics. We find that semantic memory structures are irreducible only in humans, suggesting that LLMs lack certain types of human-like conceptual knowledge. Moreover, semantic memory structure relates consistently to implicit bias only in humans, with lower levels of bias in System~2 structures. These findings suggest that certain types of conceptual knowledge contribute to bias regulation in humans, but not in LLMs, highlighting fundamental differences between human and machine cognition.

Problem

• implicit bias
• semantic memory
• System 1
• System 2
• large language models

Innovation

• semantic memory networks
• System 1 and System 2
• implicit bias
• large language models
• network analysis