LLMs for XAI: Future Directions for Explaining Explanations
This work addresses the need for more accessible explanations in AI for users and practitioners, though it is incremental as it builds on existing XAI methods.
The paper tackles the problem of making machine learning explanations more interpretable by using Large Language Models (LLMs) to refine existing XAI outputs into natural narratives, with initial experiments and a user study indicating promise for enhancing usability.
In response to the demand for Explainable Artificial Intelligence (XAI), we investigate the use of Large Language Models (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.