Case law as data : prompt engineering strategies for case outcome extraction with large language models in a zero-shot setting

HIGHLIGHTS

• What: This study evaluates the effectiveness of Large Language Models (LLMs) for automated legal outcome extraction in a zero-shot setting. The aim of this study is to show that, given precise enough instructions, State-Of-The-Art (SOTA) LLMs that can run on consumer grade hardware, already possess sufficient zero-shot capabilities for accurate extraction, with no need for further fine-tuning or bigger models. For this study, the models were accessed via the Groq REST API, a cloud-based inference service, utilizing a Python library interface implemented in Jupyter Lab. Using JSON format allows the . . .
  

   

  

  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.