Boosting Explainability and Robustness: Decision Trees from LLMs for Error Detection

This research explores a novel approach to improving the explainability and robustness of error detection by leveraging Large Language Models (LLMs) to generate decision trees. The use of ensembles of these LLM-induced decision trees represents a promising technique for practical application.

• •The core idea is to use LLMs to create decision trees.
• •This method aims to enhance both explainability and robustness.
• •Ensembling techniques are likely used to improve performance.