Tag: neural mechanisms

Source URL: https://arxiv.org/abs/2301.06627 Source: Hacker News Title: Dissociating language and thought in large language models Feedly Summary: Comments AI Summary and Description: Yes Summary: The paper titled “Dissociating language and thought in large language models” explores the capability distinction between formal and functional linguistic competences in LLMs. It evaluates how these competences relate to human…