Dissociating language and thought in large language models

arXiv:2301.06627v3 Announce Type: replace
Abstract: Large Language Models (LLMs) have come closest among all models to date to mastering human language, yet opinions about their linguistic and cognitive capabilities remain split. Here, we evaluate LLMs using a distinction between formal linguistic competence - knowledge of linguistic rules and patterns - and functional linguistic competence - understanding and using language in the world. We ground this distinction in human neuroscience, which has shown that formal and functional competence rely on different …

abstract arxiv capabilities cognitive cs.ai cs.cl functional human knowledge language language models large language large language models llms opinions patterns rules thought type