Contrasting linguistic patterns in human and llm-generated news text

HIGHLIGHTS

• What: For the generation of high-quality i text, language models aim to maximize the probability of the next word based on the previous content. Note that the LLMs the authors are using are not instruction-tuned, and thus prompting engineering is not particularly suitable, nor the goal of this work. The authors compare human- and machine-generated texts. The authors compare the degree of optimality of syntactic dependencies between human texts and LLMs.
• Who: Alberto Muñoz-Ortiz from the Universidade da Coruña, CITIC, Departamento de Ciencias de la Computación y Tecnolog . . .
  

   

  

  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.