This version provides a new LLM reasoning Model in order to evaluates the correctness and groundness of the main LLM answers. Futhermore, we provide a testing script based on some questions based on Legalbench dataset (OPP115, precisely).
This version provides a new LLM reasoning Model in order to evaluates the correctness and groundness of the main LLM answers. Futhermore, we provide a testing script based on some questions based on Legalbench dataset (OPP115, precisely).