COGNITIVE LANGUAGE MODELS IN LINGUISTICS

Abstract

This paper assesses the fundamental utility of language models in the social sciences. A simulation perspective is presented, in which language models offer a new paradigm for role simulation and modeling of cognitive processes. We discuss limitations and considerations of internal, external, construct, and statistical validity, and provide methodological recommendations for the effective integration of language models into psychological research. This perspective reexamines the role of language models in behavioral and cognitive science and sheds light on the similarities and differences between machine intelligence and human cognition and thought.

Keywords: Generative Artificial Intelligence (GenAI), Large Language Models (LLM), Simulation, Modeling.