Large language models surpass human experts in predicting neuroscience results

HIGHLIGHTS

• What: In this contribution, the authors focused on neuroscience but the aims are broader; the authors hope to provide a template for any knowledge-intensive field.
• Who: Xiaoliang Luo from the Faculty/academic staff have published the research work: Large language models surpass human experts in predicting neuroscience results, in the Journal: (JOURNAL)
• How: The authors analysed whether LLMs benefitted from a general neuroscience context (similar to few-shot prompting) rather than integrating study-relevant information. To investigate the extent to which LLMs can integrate broad context from abstracts the authors conducted an . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.