Book chapter · Advances in computational intelligence and robotics book series · April 28, 2026
Explainable AI (XAI) for Classical ML and LLMs
Brijendra Parasnath Gupta, Ergashev Nuriddin Gayratovich, Erkin Kholiyarov, Rajabov Nazirjon, Otajonova Gulkhayo, Jumayev Akbar Mahmudovich
Abstract
Explainable Artificial Intelligence (XAI) constitutes a foundational pillar of responsible AI deployment, addressing the opacity of data-driven decision systems by making their internal logic transparent, auditable, and contestable. This chapter provides a systematic account of explainability and interpretability across the full spectrum of AI models — from classical supervised learning algorithms such as decision trees, support vector machines, and gradient-boosted ensembles to contemporary Large Language Models (LLMs) built on transformer architectures. Beginning with a structured taxonomy of XAI properties — scope, stage, model-dependency, and output type — the chapter critically examines canonical explanation methods including SHAP, LIME, attention visualization, mechanistic circuit analysis, and counterfactual generation.
More by Nazirjon Rajabov
- Intelligent Assistive Technologies in Higher EducationAdvances in computational intelligence and robotics book series · 2026
- AI-Driven Cold Chain Optimization for Reducing Food Loss in Perishable Supply ChainsAdvances in computational intelligence and robotics book series · 2026
- Generative AI and Foundation Models: Governance, Ethics, and Democratic ImplicationsAdvances in computational intelligence and robotics book series · 2026
- Implementing Clean Energy Solutions for Sustainable Corporate OperationsIGI Global eBooks · 2026
