However, rather than utilizing a large language model to generate an explanation in natural language, the researchers use the LLM to transform an existing SHAP explanation into a readable narrative.

Machine-learning algorithms can make mistakes and be difficult to use, so scientists at the Massachusetts Institute of Technology created explanation methods to assist users in understanding when ...

The way that this is generally dealt with by LLM companies such as OpenAI is ... this answer from the official policy document link. An explanation could be that the backing model was trained ...