Wellawatte Geemi P, Schwaller Philippe
Laboratory of Artificial Chemical Intelligence, Institute of Chemical Sciences and Engineering, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland.
National Centre of Competence in Research (NCCR) Catalysis, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland.
Commun Chem. 2025 Jan 14;8(1):11. doi: 10.1038/s42004-024-01393-y.
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.
可解释人工智能（XAI）是人工智能领域中一个新兴的领域，旨在解决机器学习模型不透明的本质问题。此外，研究表明XAI可用于提取输入-输出关系，使其成为化学领域中理解结构-性质关系的有用工具。然而，XAI方法的主要局限性之一在于它们是为技术导向型用户开发的。我们提出了XpertAI框架，该框架将XAI方法与可访问科学文献的大语言模型（LLMs）相结合，以自动生成对原始化学数据的易懂自然语言解释。我们进行了5个案例研究来评估XpertAI的性能。我们的结果表明，XpertAI在生成具体、科学且可解释的解释方面结合了大语言模型和XAI工具的优势。
