LLMs for XAI: Future Directions for Explaining Explanations (2405.06064v1)

Abstract: In response to the demand for Explainable Artificial Intelligence (XAI), we investigate the use of LLMs to transform ML explanations into natural, human-readable narratives. Rather than directly explaining ML models using LLMs, we focus on refining explanations computed using existing XAI algorithms. We outline several research directions, including defining evaluation metrics, prompt design, comparing LLM models, exploring further training methods, and integrating external data. Initial experiments and user study suggest that LLMs offer a promising way to enhance the interpretability and usability of XAI.