Large Language Models as Psychological Simulators
A Methodological Guide
Bibliographic Data
| ID | 22434920 |
|---|---|
| Authors | Zhicheng Lin (0000-0002-6864-6559, University of Science and Technology of China, corresponding author) |
| Year | 2026 |
| Volume | 9 |
| Issue | 1 |
| Publication date | 2026-01-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Advances in Methods and Practices in Psychological Science (JOURNAL) |
| Journal identifiers | ISSN: 2515-2459 • E-ISSN: 2515-2467 |
| Publisher | SAGE Publications (PUBLISHER • US) |
| DOI | 10.1177/25152459251410153 |
| OpenAlex | W4417539309 |
| Language | EN |
| Citations received | 1 |
| References cited | 89 |
Large language models (LLMs) offer emerging opportunities for psychological and behavioral research, but methodological guidance is lacking. In this article, I develop a framework for using LLMs as psychological simulators across two primary applications: simulating roles and personas to explore diverse contexts, and serving as computational models to investigate cognitive processes. For simulation, the framework includes (a) an implementation-confound checklist distinguishing essential from context-dependent methodological checks, (b) methods for developing psychologically grounded personas that move beyond demographic categories, and (c) a three-tier validation framework (direct, indirect, and generative) tailored to data availability. A diagnostic decision framework guides researchers through establishing performance validity, identifying implementation artifacts, and interpreting LLM-human discrepancies. For cognitive modeling, I synthesize (a) emerging approaches for probing internal representations, (b) methodological advances in causal interventions, and (c) strategies for relating model behavior to human cognition. The framework addresses overarching challenges, including prompt sensitivity, temporal limitations from training-data cutoffs, and ethical considerations that extend beyond traditional human-subjects review. Open-weight models are the default for reproducibility. Together, this framework integrates emerging empirical evidence about LLM performance—including systematic biases, cultural limitations, and prompt brittleness—to help researchers wrangle these challenges and leverage the unique capabilities of LLMs in psychological research.
Cognition · Cognitive interview · Empirical research · Persona · Psychological research · Mental Health via Writing · Persona Design and Applications · Topic Modeling
Parallel Distributed Processing
Agent-based modeling
Cultural bias and cultural alignment of large language models
AI and the transformation of social science research
Generative Agents
Elements of a theory of human problem solving.
Using cognitive psychology to understand GPT-3
The Cognitive Reflection Test as a predictor of performance on heuristics-and-biases tasks
Performance and biases of Large Language Models in public opinion simulation
Large Language Models and the Wisdom of Small Crowds
The Limitations of Large Language Models for Understanding Human Language and Cognition
Large language models are better than theoretical linguists at theoretical linguistics
Probing Classifiers
Large language models can replicate cross-cultural differences in personality
Dynamic models of segregation
Black Boxes or Unflattering Mirrors? Comparative Bias in the Science of Machine Behaviour
You don't know me, but I know you
Can Large Language Models Transform Computational Social Science
Using deep neural networks to disentangle visual and semantic information in human perception and memory
Testing theory of mind in large language models and humans
Active use of latent tree-structured sentence representation in humans and large language models
How to write effective prompts for large language models
| Unique citing works | 1 |
|---|---|
| Citations per year | 1 |
| Citation span | 2026 - 2026 (1) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 1 |