Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review
This review explores the frontiers of large language models (LLMs) in psychological applications. Psychology has undergone several theoretical changes, and the current use of artificial intelligence (AI) and machine learning, particularly LLMs, promises to open up new research directions. We aim to provide a detailed exploration of how LLMs are transforming psychological research. We discuss the impact of LLMs across various branches of psychology—including cognitive and behavioral, clinical and counseling, educational and developmental, and social and cultural psychology—highlighting their ability to model patterns, cognition, and behavior similar to those observed in humans. Furthermore, we explore the ability of such models to generate coherent, contextually relevant text, offering innovative tools for literature reviews, hypothesis generation, experimental designs, experimental subjects, and data analysis in psychology. We emphasize the importance of addressing technical and ethical challenges, including data privacy, the ethics of using LLMs in psychological research, and the need for a deeper understanding of these models’ limitations.
Introduction. Artificial intelligence (AI) has a history spanning nearly seven decades, beginning with the 1956 Dartmouth Conference. The field has recently been revolutionized with the advent of large language models (LLMs) such as ChatGPT, Google’s Bard, and Meta’s LLaMA. Among them, GPT-4, in particular, could signify a paradigm shift given its impressive capabilities (e.g., solving difficult tasks in math, coding, vision,
Lines of inquiry this paper opens 24
Research framings built by reading the notes related to this paper — the questions it feeds into.
What determines whether language models adopt prompted personas successfully?- How do LLM behavioral profiles differ across prompt registers like advice versus task execution?
- Why do questionnaire-based personality scores fail to predict actual LLM behavioral choices?
- How does personality priming change LLM strategic decision making?
- Do psychological test methods reveal LLM associations that direct questions hide?
- How can we validate LLM-based drift measurements against human judgment?
- How do bimodal decision patterns in LLMs compare to human economic choice?
- How does language condition affect model psychological profile consistency?
- Which other LLM pairs show equally distinctive and readable fingerprints in their outputs?
- Does approaching human performance mean learning the same grammatical rules?
- How much of LLM behavior traces to post-training reward signals?
- Do token probability distributions in LLMs track human reaction time patterns?
- Can LLMs infer situational context the way humans do pragmatically?
- Can language models develop world models that ground meaning in causal reality?
- Can statistical learning from language alone capture all aspects of cultural competence?
- Do language models calibrate to actual human pragmatic norms?