Extracting human interpretable structure-property relationships in chemistry using XAI and large language models
This addresses the need for interpretable AI tools in chemistry for non-technical users, though it appears incremental by combining existing XAI and LLM methods.
The authors tackled the problem of making XAI methods accessible to non-technical users in chemistry by proposing the XpertAI framework, which integrates XAI with large language models to generate natural language explanations from raw chemical data, and results from 5 case studies show it produces specific, scientific, and interpretable explanations.
Explainable Artificial Intelligence (XAI) is an emerging field in AI that aims to address the opaque nature of machine learning models. Furthermore, it has been shown that XAI can be used to extract input-output relationships, making them a useful tool in chemistry to understand structure-property relationships. However, one of the main limitations of XAI methods is that they are developed for technically oriented users. We propose the XpertAI framework that integrates XAI methods with large language models (LLMs) accessing scientific literature to generate accessible natural language explanations of raw chemical data automatically. We conducted 5 case studies to evaluate the performance of XpertAI. Our results show that XpertAI combines the strengths of LLMs and XAI tools in generating specific, scientific, and interpretable explanations.