The Mind in the Machine: A Survey of Incorporating Psychological Theories in LLMs
Zizhou Liu, Ziwei Gong, Lin Ai, Zheng Hui, Run Chen, Colin Wayne Leach, Michelle R. Greene, Julia Hirschberg
TL;DR
The paper addresses the lack of a unified map for integrating diverse psychological theories into LLM development across preprocessing, pre-training, post-training, and evaluation. It provides a stage-wise synthesis drawing on cognitive, developmental, behavioral, social, personality, and psycholinguistic theories to guide LLM design choices. Its contributions include identifying trends, gaps, under-explored concepts, and debates at the NLP–psychology interface to inform principled integration. This synthesis aims to improve alignment, interpretability, and ethical impact of LLMs by grounding development in established psychological theory.
Abstract
Psychological insights have long shaped pivotal NLP breakthroughs, including the cognitive underpinnings of attention mechanisms, formative reinforcement learning, and Theory of Mind-inspired social modeling. As Large Language Models (LLMs) continue to grow in scale and complexity, there is a rising consensus that psychology is essential for capturing human-like cognition, behavior, and interaction. This paper reviews how psychological theories can inform and enhance stages of LLM development, including data, pre-training, post-training, and evaluation\&application. Our survey integrates insights from cognitive, developmental, behavioral, social, personality psychology, and psycholinguistics. Our analysis highlights current trends and gaps in how psychological theories are applied. By examining both cross-domain connections and points of tension, we aim to bridge disciplinary divides and promote more thoughtful integration of psychology into future NLP research.
