Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models

TL;DR

This review synthesizes how large language models exhibit human-like cognitive patterns across decision-making, reasoning, and creativity, highlighting their capabilities, limitations, and potential as collaborative tools.

Contribution

It provides a comprehensive analysis of LLMs' cognitive abilities compared to humans, emphasizing emergent patterns and identifying gaps for future research.

Findings

LLMs show some human-like decision biases but lack others.

Advanced models like GPT-4 demonstrate reasoning similar to human System-2 thinking.

LLMs excel in language-based creativity but struggle with divergent thinking tasks.

Abstract

Research on emergent patterns in Large Language Models (LLMs) has gained significant traction in both psychology and artificial intelligence, motivating the need for a comprehensive review that offers a synthesis of this complex landscape. In this article, we systematically review LLMs' capabilities across three important cognitive domains: decision-making biases, reasoning, and creativity. We use empirical studies drawing on established psychological tests and compare LLMs' performance to human benchmarks. On decision-making, our synthesis reveals that while LLMs demonstrate several human-like biases, some biases observed in humans are absent, indicating cognitive patterns that only partially align with human decision-making. On reasoning, advanced LLMs like GPT-4 exhibit deliberative reasoning akin to human System-2 thinking, while smaller models fall short of human-level performance. A distinct dichotomy emerges in creativity: while LLMs excel in language-based creative tasks, such as storytelling, they struggle with divergent thinking tasks that require real-world context. Nonetheless, studies suggest that LLMs hold considerable potential as collaborators, augmenting creativity in human-machine problem-solving settings. Discussing key limitations, we also offer guidance for future research in areas such as memory, attention, and open-source model development.