Explainable AI: A Review of Machine Learning Interpretability Methods

By Pantelis Linardatos, Vasilis Papastefanopoulos, S. Kotsiantis. 2020

2,690 citations recorded by the source corpus.

Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption, with machine learning systems demonstrating superhuman performance in a significant number of tasks. However, this surge in performance, has often been achieved through increased model complexity, turning such systems into “black box” approaches and causing uncertainty regarding the way they operate and, ultimately, the way that they come to decisions. This ambiguity has made it problematic for machine learning systems to be adopted in sensitive yet critical domains, where their value could be immense, such as healthcare. As a result, scientific interest in the field of Explainable Artificial Intelligence (XAI), a field that is concerned with the development of new methods that explain and interpret machine learning models, has been tremendously reignited over recent years. This study focuses on machine learning interpretability methods; more specifically, a literature review and taxonomy of these methods are presented, as well as links to their programming implementations, in the hope that this survey would serve as a reference point for both theorists and practitioners.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Ethical and social risks of harm from Language Models (2021, background): “A range of tools has been proposed and discussed to make AI systems, and specifically NLP and language models, more explainable and interpretable (for reviews see (Belinkov and Glass, 2019; Bommasani et al., 2021; Linardatos et al., 2021)).”
AI for Next Generation Computing: Emerging Trends and Future Directions (2022, neutral): “Is a computing system stable and robust enough to execute orkloads? Are the trained models black boxes or causally explainable? These are just a few examples of challenges that are faced efore a computing system can be implemented [212].”
Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review (2023, background): “Understanding this structure involves unraveling the many layers of neural networks, the various attention mechanisms at work, and the role of individual nodes and weights in the decision-making process of these models [87].”
The rise and potential of large language model based agents: a survey (2025, neutral): “LLM-based agents have limitations because of hallucination [228], the lack of training data and tuning for speciﬁc ﬁelds [229], untransparent decision-making process [230] and susceptibility to adversarial attacks [231].”
Tool learning with large language models: a survey (2024, neutral): “Due to the diverse and multifaceted nature of user queries in the real-world, which may encompass multiple languages and modalities, LLMs often face challenges in consistently understanding different types of input.”
The Role of AI in Hospitals and Clinics: Transforming Healthcare in the 21st Century (2024, background): “Interpretability ensures that AI models provide clear explanations for their decisions, fostering trust with clinicians who can understand the reasoning behind recommendations [153].”
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, background): “2021 [85] P, R Technical, with source code 3”
Remote patient monitoring using artificial intelligence: Current state, applications, and challenges (2023, neutral): “Linardatos et al. (2020) reviewed machine learning interpretability methods.”
Tool Learning with Foundation Models (2023, neutral): “Foundation models are criticized for lacking transparency in their decision-making process (Linardatos et al., 2020), which can be a significant concern in applications such as healthcare or finance, where interpretability is critical for making informed decisions.”
Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021, methodology): “A rapid advancement of XAI is evident, and the recent study by Linardatos et al. [132] has identiﬁed four main areas of focus: methods for explaining complex black-box models, methods for creating white-box models, methods that promote fairness and restrict the existence of discrimination, and…”
Cross-Loss Influence Functions to Explain Deep Network Representations (2020, background): “…have been proposed, including interpretable neural network approaches (Wang et al., 2016), natural language generation of explanations (Mullenbach et al., 2018; Wiegreﬀe and Pinter, 2019; Chen et al., 2021), and many others Hoﬀman et al. (2018); Holzinger et al. (2020); Linardatos et al. (2021).”
Framework for Evaluating LLM Performance in Undergraduate Calculus (2026, unknown): “Finally, broader surveys in explainable ML [18,19] identify key metrics of explanatory quality, such as cognitive load, user trust, and task relevance.”
SAGE-RAI: Design Patterns for Transparent RAG Systems (2026, unknown): “ExplainabilityandTrust: XAIliteraturedistinguishes interpretable and actionable [8, 21].”
Interpretability Framework for LLMs in Undergraduate Calculus (2025, unknown): “Finally, broader surveys in explainable ML [10, 11] identify key metrics of explanatory quality, such as cognitive load, user trust, and task relevance.”