Running cognitive evaluations on large language models: The do's and the don'ts

Ever since the Turing test [Turing, 1950], the idea of having a dialogue with a machine to probe its cognitive abilities ("thought") has been inextricably associated with the field of artificial intelligence (AI). In addition to its intuitive simplicity, this idea naturally aligns with everyday practice in psychology: language-based assessments are the bread and butter of many psychologists' toolkits. If researchers want to know what is happening in the mind of a human, the easiest approach is to ask. Today, advances in linguistic abilities of large language models (LLMs) make it possible to seamlessly test these models on language-based assessments originally designed for people. This is an unprecedented advance: to date, the only entities who could flexibly use human language were, well, humans. Now, however, we are faced with artificial systems that can process linguistic information, generate novel texts, and respond to questions. How do we assess the cognitive capabilities of these systems? Easy access to chat-based LLM interfaces (the most famous of which is ChatGPT) makes it possible for anyone to run a "cognitive test" on an AI system. This advance has led to an explosive growth of what one might call AI psychology (or machine psychology; Hagendorff 2023b), with papers assessing LLMs' personality traits [Jiang et al., 2023, Safdari et al., 2023], working memory capacity [Gong et al., 2023], logical