Integrating human knowledge for explainable AI

• Published in: Machine learning Vol. 114; no. 11; p. 250
• Main Authors: Cappuccio, Eleonora, Kathirgamanathan, Bahavathy, Rinzivillo, Salvatore, Andrienko, Gennady, Andrienko, Natalia
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2025; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Collaboration; Computer Science; Control; Engineering; Explainable artificial intelligence; Knowledge; Large language models; Logic; Machine Learning; Mechatronics; Natural Language Processing (NLP); Neighborhoods; Robotics; Semantics; Simulation and Modeling; Subject specialists; Visual analytics; Knowledge-guided explainable AI (XAI); Trustworthy AI
• ISSN: 0885-6125; 1573-0565; 1573-0565
• DOI: 10.1007/s10994-025-06879-x

This paper presents a methodology for integrating human expert knowledge into machine learning (ML) workflows to improve both model interpretability and the quality of explanations produced by explainable AI (XAI) techniques. We strive to enhance standard ML and XAI pipelines without modifying underlying algorithms, focusing instead on embedding domain knowledge at two stages: (1) during model development through expert-guided data structuring and feature engineering, and (2) during explanation generation via domain-aware synthetic neighbourhoods. Visual analytics is used to support experts in transforming raw data into semantically richer representations. We validate the methodology in two case studies: predicting COVID-19 incidence and classifying vessel movement patterns. The studies demonstrated improved alignment of models with expert reasoning and better quality of synthetic neighbourhoods. We also explore using large language models (LLMs) to assist experts in developing domain-compliant data generators. Our findings highlight both the benefits and limitations of existing XAI methods and point to a research direction for addressing these gaps.