PolyU-led research reveals that sensory and motor inputs help large language models represent complex concepts (IMAGE)
Caption
The research team selected conceptual word ratings produced by state-of-the-art LLMs, namely ChatGPT and Google LLMs, and compared them with human-generated word ratings of around 4,500 words across non-sensorimotor, sensory and motor domains from the Glasgow Norms and Lancaster Norms datasets.
Credit
© 2025 Research and Innovation Office, The Hong Kong Polytechnic University. All Rights Reserved.
Usage Restrictions
nil
License
Original content