Explainable AI: A Review of Machine Learning Interpretability Methods
Open accessThe DOI matches its Crossref record; 170 of the 170 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“While valuable, these techniques can sometimes be inconsistent or fail to capture the true decision-making process of highly complex models, potentially leading to a false sense of interpretability66.”
From Bias recognition and mitigation strategies in artificial intelligence healthcare applications (2025) · cites this paper as [66]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These methods facilitate a deeper understanding of the model’s internal logic, support debugging and optimization processes, and help identify key variables that most strongly influence students’ behavioral intentions toward GenAI adoption (Linardatos et al., 2020).”
From A two-step structural equation modeling and explainable machine learning framework for understanding university students’ adoption of generative AI: balancing intrinsic motivations and perceived risks (2026) · cites this paper as Linardatos et al., 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Yet, there is no common taxonomy neither within one field (such as data science) nor between different fields (law and data science).”
From Transparency of AI in Healthcare as a Multilayered System of Accountabilities: Between Legal Requirements and Technical Limitations (2022) · cites this paper as Linardatos et al., 2021
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Despite the substantial amount of research devoted to solving the black-box issue of AI, many scholars in the field agree that a clear relevant taxonomy is missing (Doshi-Velez and Kim, 2017; Adadi and Berrada, 2018; Linardatos et al., 2021).”
From Transparency of AI in Healthcare as a Multilayered System of Accountabilities: Between Legal Requirements and Technical Limitations (2022) · cites this paper as Linardatos et al., 2021
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Prior research on XAI across industries, has also found that the perceived quality of explanations is closely tied to their actionability and practical relevance for end users [8].”
From Explainable AI in hospital clinical decision support systems: A scoping review of healthcare professionals’ perspectives (2026) · cites this paper as [8]
Experimental — accuracy not yet measured
5 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“An improvement over the initial method was proposed in [24], where the well-known Krizhevsky network [25] was utilised in order to outperform state-of-the-art saliency models by a large margin, increasing the amount of explained information by 67% when compared to state-of-the art.”
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · cited 1×
“On the one hand, there are the so called black-box models, which include deep learning [2] and ensembles [8–10].”
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731 · cited 3×
“[59] PDPbox InterpretML Skater PH G Agnostic tab 589.”
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 3×
“The breakDown method, as proposed in [62], is similar to SHAP [48], as both, based on the conditioned responses of a black-box model, attempt to attribute them proportionally to the input features.”
Classification and Regression by randomForest
Liaw, A. I., & Wiener, M. C. (2007) · Cited by 18,594
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 8×
“[44] showed that, while the Deconvolution [32], Guided BackPropagation [31], and LRP [37] methods help in interpreting deep neural networks, they do not produce the theoretically correct interpretation, even in the simplest neural network setting; a linear model developed while using data that were produced by a linea…”
InfluentialLearning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428 · cited 2×
“In many cases, this is achieved through exploiting the gradient information flowing through the layers of the network, Grad-CAM [35], a direct extension of [34], being a prime and most influential example in terms of citations per year.”
Research works printed but not linked: 3
- Luss, R., Chen, P.Y., Dhurandhar, A., Sattigeri, P., Zhang, Y., Shanmugam, K., and Tu, C.C. (2019). Generating contrastive explanations with monotonic attribute functions. arXiv.
- Van Looveren, A., and Klaise, J. (2019). Interpretable counterfactual explanations guided by prototypes. arXiv.
- Wang, X., Jin, H., and He, K. (2019). Natural language adversarial attacks and defenses in word level. arXiv.
Cited by
Items 901–1,000 of 1,016
Li, W., Zhan, W., Han, T., Wang, P., Liu, H., Xiong, M., & Hong, S. (2022) · Journal of Signal Processing Systems · doi:10.1007/s11265-022-01816-w · Cited by 16
“In recent years, machine learning [4, 5] and neural network algorithms have developed rapidly, facilitating the advancement of deep learning [6].”
BackgroundBlack-box error diagnosis in Deep Neural Networks for computer vision: a survey of tools
Fraternali, P., Milani, F., Torres, R. N., & Zangrando, N. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-08100-9 · Cited by 18
“The difference between interpretability and explainability is subtle: the former emphasizes human intuition whereas the latter stresses the comprehension of the internal logic of the model [17].”
BackgroundInterpretable Privacy-Preserving Collaborative Deep Learning for Taxi Trip Duration Forecasting
Fiošina, J. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-17098-0_20 · Cited by 26
From bias to black boxes: understanding and managing the risks of AI – an actuarial perspective
du Preez, V., Bennet, S., Byrne, M., Couloumy, A., Das, A., Dessain, J., Galbraith, R., King, P., Mutanga, V., Schiller, F., et al. (2024) · British Actuarial Journal · doi:10.1017/s1357321724000060 · Cited by 15
Network-based analyses of multiomics data in biomedicine
Kumar, R., Romano, J. D., & Ritchie, M. D. (2025) · BioData Mining · doi:10.1186/s13040-025-00452-x · Cited by 19
“By their nature, they attempt to incorporate and model potential nonlinear relationships between their feature set at each step, which makes understanding the exact relationship of a feature to the output or to intermediate learned features difficult [59, 60, 61].”
Artificial Intelligence in Advancing Inflammatory Bowel Disease Management: Setting New Standards
Labarile, N., Vitello, A., Sinagra, E., Nardone, O. M., Calabrese, G., Bonomo, F., Maida, M. F., & Iacucci, M. (2025) · Cancers · doi:10.3390/cancers17142337 · Cited by 17
“Additionally, because tagged data forms the basis of most existing AI models, interpretability depends on the accuracy of the observer who labelled the “gold standard” data [105,106].”
Explainable person–job recommendations: challenges, approaches, and comparative analysis
Tang, F., Zhu, R., Yao, F., Wang, J., Luo, L., & Li, B. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1660548 · Cited by 24
A Multi-Criteria Decision-Making Approach for the Selection of Explainable AI Methods
Matejová, M., & Paralič, J. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7040158 · Cited by 17
“The terms interpretability and explainability are often used interchangeably by researchers [2].”
Mechanistically guided residual learning for battery state monitoring throughout life
Che, Y., Zheng, Y., Rhyu, J., Guo, J., Wang, S., Teodorescu, R., & Braatz, R. D. (2026) · Nature Communications · doi:10.1038/s41467-025-67565-z · Cited by 26
Explainable Artificial Intelligence Approaches: Challenges and Perspectives
Shevskaya, N. V. (2021) · International Conference "Quality Management, Transport and Information Security, Information Technologies" (IT&QM&IS) · doi:10.1109/itqmis53292.2021.9642869 · Cited by 15
Shimazaki, T., & Tachikawa, M. (2022) · ACS Omega · doi:10.1021/acsomega.1c06976 · Cited by 16
Learning Interpretable, High-Performing Policies for Autonomous Driving
Paleja, R., Niu, Y., Silva, A., Ritchie, C., Choi, S., & Gombolay, M. (2022) · Robotics: Science and Systems · doi:10.15607/rss.2022.xviii.068 · Cited by 33
“Explainable AI (xAI) is concerned with understanding and interpreting the behavior of AI systems [39].”
BackgroundUsing explainability to design physics-aware CNNs for solving subsurface inverse problems
Crocker, J., Kumar, K., & Cox, B. R. (2023) · Computers and Geotechnics · doi:10.1016/j.compgeo.2023.105452 · Cited by 20
Symmetry preserving neural network models for spur gear static transmission error curves
Sakaridis, E., Kalligeros, C., Papalexis, C., Kostopoulos, G., & Spitas, V. (2023) · Mechanism and Machine Theory · doi:10.1016/j.mechmachtheory.2023.105369 · Cited by 15
Artificial Intelligence and the Digital Twin: An Essential Combination
Minerva, R., Crespi, N., Farahbakhsh, R., & Awan, F. M. (2023) · Springer eBooks · doi:10.1007/978-3-031-21343-4_12 · Cited by 22
Tian, Q., Gao, H., Tian, Y., Jiang, Y., Li, Z., & Guo, L. (2023) · Water · doi:10.3390/w15183184 · Cited by 16
Nasir, V., Schimleck, L. R., Abdoli, F., Rashidi, M., Sassani, F., & Avramidis, S. (2023) · Polymers · doi:10.3390/polym15204147 · Cited by 15
“Machine learning interpretability methods have been reviewed in the literature [39,40], among which feature importance ranking is a powerful tool for XAI [41].”
MethodExplainable AI (XAI) for AI-Acceptability: The Coming Age of Digital Management 5.0
Gamoura, S. C. (2023) · IEEE International Conference on Networking, Sensing and Control (ICNSC) · doi:10.1109/icnsc58704.2023.10319030 · Cited by 17
Jeyaraman, M., Ratna, H. V. K., Jeyaraman, N., Venkatesan, A. S., Ramasubramanian, S., & Yadav, S. (2023) · Cureus · doi:10.7759/cureus.49756 · Cited by 27
“ML algorithms can learn from examples by adjusting their internal parameters (weights) and strengthening relevant associations to improve the accuracy of a given model [22-24].”
BackgroundExplainable Machine Learning for LoRaWAN Link Budget Analysis and Modeling
Hosseinzadeh, S., Ashawa, M., Owoh, N. P., Larijani, H., & Curtis, K. (2024) · Sensors · doi:10.3390/s24030860 · Cited by 15
“Finally, decision trees are chosen for being effective and having excellent AI explainability (XAI) [37].”
BackgroundKoulinas, G. K., Paraschos, P. D., & Koulouriotis, D. E. (2024) · Flexible Services and Manufacturing Journal · doi:10.1007/s10696-024-09537-x · Cited by 21
“…that explainability in machine learning algorithms refers to the ability to understand and interpret the output or decision made by the algorithm (Linardatos et al. 2021), we performed additional research to assess the influence of tree algorithmic factors on their efficacy, and make the model…”
Niu, W., Feng, Y., Xu, S., Wilson, A. D., Jin, Y., Ma, Z., & Wang, Y. Y. (2024) · Computers in Human Behavior · doi:10.1016/j.chb.2024.108272 · Cited by 18
Lee, S., Kareem, A. B., & Hur, J.-W. (2024) · Electronics · doi:10.3390/electronics13091700 · Cited by 15
“Furthermore, interpreting these models’ learned representations and decision-making processes can be challenging, hindering trust and acceptance, particularly in critical domains like industrial systems [64].”
The influence of perovskite crystal structure on its stability
Bi, H., Wang, M., Liu, L., Yan, J., Zeng, R., Zhang, X., & Wang, J. (2024) · Journal of Materials Chemistry A · doi:10.1039/d3ta07457a · Cited by 15
Unveiling the factors of aesthetic preferences with explainable AI
Soydaner, D., & Wagemans, J. P. (2024) · British Journal of Psychology · doi:10.1111/bjop.12707 · Cited by 22
“Addressing this need, the field of XAI has gained significant attention (Biran & Cotton, 2017; Gohel et al., 2021; Holzinger et al., 2022; Linardatos et al., 2020).”
Deep Neural Networks for Anti Money Laundering Using Explainable Artificial Intelligence
Konstantinidis, G., & GEGOV, A. E. (2024) · IEEE International Conference on Intelligent Systems · doi:10.1109/is61756.2024.10705194 · Cited by 15
“LIME approximates the model’s behavior near a specific instance by fitting an interpretable surrogate model [12], [14].”
BackgroundMethodComplexity data science: A spin-off from digital twins
Emmert‐Streib, F., Cherifi, H., Kaski, K. K., Kauffman, S. A., & Yli-Harja, O. P. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae456 · Cited by 17
Gogoi, P., & Valan, J. A. (2024) · Biomedical Materials & Devices · doi:10.1007/s44174-024-00262-5 · Cited by 20
Embodied AI with Two Arms: Zero-shot Learning, Safety and Modularity
Varley, J., Singh, S., Jain, D., Choromański, K., Zeng, A., Chowdhury, S. B. R., Dubey, A., & Sindhwani, V. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802181 · Cited by 38
“Modular architectures may facilitate explainability and interpretability [24], which may mitigate such concerns.”
Ho, N. T. N., Gonzalez, P., & Gogovi, G. K. (2025) · Healthcare Technology Letters · doi:10.1049/htl2.70006 · Cited by 20
Explaining Youth Driver Licensing Determinants Using XGBoost and SHAP
Wang, K., Vos, J. D., Smart, M., & Wang, S. (2025) · Transport Policy · doi:10.1016/j.tranpol.2025.04.009 · Cited by 18
Mohammed, M., Oleiwi, J. K., Mohammed, A. M., Osman, A. F., Adam, T., Betar, B. O., & Gopinath, S. C. B. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110933 · Cited by 18
Kanakaris, N., Giarelis, N., Siachos, I., & Karacapilidis, N. I. (2021) · Entropy · doi:10.3390/e23060664 · Cited by 18
Oei, R. W., Lyu, Y., Ye, L., Kong, F., Du, C., Zhai, R., Xu, T., Shen, C., He, X., Kong, L., et al. (2021) · Journal of Personalized Medicine · doi:10.3390/jpm11080787 · Cited by 15
Strategies for Sudden Cardiac Death Prevention
Corianò, M., & Tona, F. (2022) · Biomedicines · doi:10.3390/biomedicines10030639 · Cited by 16
Lo, S., & Yin, Y. (2021) · Discover Artificial Intelligence · doi:10.1007/s44163-021-00015-z · Cited by 15
“In addressing the concepts of interpretability and explainability, these scholars and researchers have made attempts towards discussing a trade-off between learning performance (usually measured by prediction performance) and effectiveness of explanations (also known as explainability) is presented in Figure 1 [2] [3].”
BackgroundAutomatic Interpretable Personalized Learning
Prihar, E., Haim, A., Sales, A., & Heffernan, N. T. (2022) · ACM Conference on Learning @ Scale (L@S) · doi:10.1145/3491140.3528267 · Cited by 20
Algorithm Assurance: Auditing Applications of Artificial Intelligence
Boer, A., de Beer, L., & van Praat, F. (2022) · Progress in IS · doi:10.1007/978-3-031-11089-4_7 · Cited by 24
Benchmarking explanation methods for mental state decoding with deep learning models
Thomas, A. W., Ré, C., & Poldrack, R. A. (2023) · NeuroImage · doi:10.1016/j.neuroimage.2023.120109 · Cited by 18
“From the wealth of existing explanation methods (Gilpin et al., 2018; Linardatos et al., 2021), neuroimaging researchers most often utilize attribution (i.”
González‐González, J., de Arriba-Pérez, F., García-Méndez, S., Busto-Castiñeira, A., & González-Castaño, F. J. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.101634 · Cited by 18
“In this regard, safety and interpretability (Carvalho et al., 2019; Linardatos et al., 2020) pursue the extraction of knowledge from the trained classifiers by traversing the decision tree paths to better understand the performance of the ML model.”
Gallo, M., Gallo, M., Nenutil, R., Němeček, M., Holub, P., & Brázdil, T. (2023) · New Biotechnology · doi:10.1016/j.nbt.2023.09.008 · Cited by 20
Pandey, C., Angryk, R. A., Georgoulis, M. K., & Aydin, B. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-45275-8_38 · Cited by 16
“These are post hoc analysis methods (attribution meth-ods) [12], meaning they focus on the analysis of trained models and do not contribute to the models’ parameters while training.”
BackgroundMethodPersonalized stratification of hospitalization risk amidst COVID-19: A machine learning approach
Lam, C., Calvert, J. S., Siefkas, A. C., Barnes, G., Pellegrini, E., Green‐Saxena, A., Hoffman, J. L., Mao, Q., & Das, R. (2021) · Health Policy and Technology · doi:10.1016/j.hlpt.2021.100554 · Cited by 15
“Developing effective algorithms for use in public health settings and that complement established guidelines, such as the OUAA guidelines, may complement efforts to develop explainable AI [23] and help to bolster support for such algorithms in both current and future infectious outbreaks.”
Diagnosing AI Explanation Methods with Folk Concepts of Behavior
Jacovi, A., Bastings, J., Gehrmann, S., Goldberg, Y., & Filippova, K. (2023) · Journal of Artificial Intelligence Research · doi:10.1145/3593013.3593993 · Cited by 30
Explainable AI for Fault Detection and Classification in Microgrids
Ajayi, O., Mirjafari, M., Idowu, P. B., & Ullah, M. H. (2024) · IEEE Energy Conversion Congress and Exposition (ECCE) · doi:10.1109/ecce55643.2024.10861648 · Cited by 15
“They help identify influential input features, validate the model’s reasoning, and enhance trustwor-thiness [17].”
Applying Machine Learning Techniques to Predict Drug-Related Side Effect: A Policy Brief
Toni, E., & Ayatollahi, H. (2025) · INQUIRY The Journal of Health Care Organization Provision and Financing · doi:10.1177/00469580251335805 · Cited by 19
Defining deliberation for dual-process models of reasoning
Neys, W. D. (2025) · Nature Reviews Psychology · doi:10.1038/s44159-025-00466-6 · Cited by 22
“It seeks to provide clear, accessible justifications or explanations for AI outputs — especially in high-stakes domains such as healthcare, finance or criminal justice — so that users can understand how and why a particular recommendation or decision was made 100 .”
Pinto, I., Olazarán, Á., Jurío, D., de la Osa, B., Sainz, M., Oscoz, A., Ballaz, J., Gorricho, J., Galar, M., & Andonegui, J. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1547045 · Cited by 16
Machine learning-driven insights into the microstructure and properties of high-entropy alloys
Zhang, X., Zhou, W., Li, X., Xu, T., Yu, Y., Zheng, L., Jin, G., & Zhang, S. (2025) · Advanced Powder Materials · doi:10.1016/j.apmate.2025.100331 · Cited by 28
Lee, J. U., & Kim, H. J. (2025) · BioChip Journal · doi:10.1007/s13206-025-00229-8 · Cited by 18
“To address this, recent efforts have focused on developing “explainable” ML algorithms [83].”
Ensemble learning approach with explainable AI for improved heart disease prediction
Adekoya, A., Saeed, F., Ghaban, W., & Qasem, S. N. (2025) · Frontiers in Pharmacology · doi:10.3389/fphar.2025.1654681 · Cited by 24
Audience-Dependent Explanations for AI-Based Risk Management Tools: A Survey
Misheva, B. H., Jaggi, D., Posth, J.-A., Gramespacher, T., & Osterrieder, J. R. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.794996 · Cited by 22
“In general, methods are considered in view of two main criteria (Linardatos et al. 2021): 1) the type of algorithm on which they can be applied (model-speci fi c vs. model-agnostic) and 2) the unit being explained (if the method provides an explanation which is instance-speci fi c then this is a…”
MethodAtkinson, P. M., Stein, A., & Jeganathan, C. (2022) · Spatial Statistics · doi:10.1016/j.spasta.2022.100646 · Cited by 14
Yong, B. X., & Brintrup, A. M. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.108912 · Cited by 18
From Explainability to Ineffability? ML Tarot and the Possibility of Inspiriting Design
Lustig, C., & Rosner, D. K. (2022) · Designing Interactive Systems Conference · doi:10.1145/3532106.3533552 · Cited by 16
Hartwich, E., Rieger, A., Sedlmeir, J., Jurek, D., & Fridgen, G. (2023) · Electronic Markets · doi:10.1007/s12525-023-00649-0 · Cited by 18
“In particular, it will be important to unpack to what extent self-assigned goals need to be reproducible and explainable to constitute rationality and consistent preferences (Linardatos et al., 2020).”
BackgroundQin, X., Ran, T., Chen, Y., Zhang, Y., Wang, D., Zhou, C., & Zou, D. (2023) · Diagnostics · doi:10.3390/diagnostics13193054 · Cited by 16
“…renewing pathologists’ interest in 5 of 14 Interpretability meth-ods, such as Grad-CAM and AGF-Visualization, generate visual explanations for corresponding class labels, increasing the transparency of AI algorithms and enabling human scrutiny to detect undesirable AI behavior (Figure 2) [51,52].”
BackgroundMethodEvaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability
Mikriukov, G., Schwalbe, G., Hellert, C., & Bade, K. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44067-0_26 · Cited by 20
“XAI is a subfield of AI that focuses on revealing the inner workings of blackbox models in a way that humans can understand [37,5,27].”
BackgroundA unified and practical user-centric framework for explainable artificial intelligence
Kaplan, S., Uusitalo, H. M. T., & Lensu, L. T. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111107 · Cited by 31
Formal and Practical Elements for the Certification of Machine Learning Systems
Durand, J.-G., Dubois, A., & Moss, R. J. (2023) · IEEE/AIAA Digital Avionics Systems Conference (DASC) · doi:10.1109/dasc58513.2023.10311201 · Cited by 15
“2) Explainability: A large body of work focuses on making neural networks interpretable by peeking into the hidden layers [31].”
BackgroundZhao, H., Jiming, E., Chen, S., Cheng, G., & Guo, F. (2023) · Tribology International · doi:10.1016/j.triboint.2023.109184 · Cited by 14
Understanding imbalanced data: XAI & interpretable ML framework
Dablain, D. A., Bellinger, C., Krawczyk, B., Aha, D. W., & Chawla, N. V. (2024) · Machine Learning · doi:10.1007/s10994-023-06414-w · Cited by 21
“We use both terms (XAI and IML) in this paper, since no clear, commonly agreed upon definition of explanation and interpretation exists (Linardatos et al., 2020).”
Machine learning identifies key metabolic reactions in bacterial growth on different carbon sources
Woo, H., Kim, Y.-S., Kim, D., & Yoon, S. H. (2024) · Molecular Systems Biology · doi:10.1038/s44320-024-00017-w · Cited by 16
“In contrast, complex DL methods have a high prediction accuracy for the black-box problem (Linardatos et al, 2020).”
BackgroundBoutet, A., Haile, S. S., Yang, A. Z., Son, H. J., Malik, M., Pai, V., Nasralla, M., Germann, J., Vetkas, A., Khalvati, F., et al. (2024) · American Journal of Neuroradiology · doi:10.3174/ajnr.a8252 · Cited by 17
Mercier, M., Pepi, C., Pavia, G. C., BENEDICTIS, A. D., Rossi‐Espagnet, M. C., Pirani, G., Vigevano, F., Marras, C. E., Specchio, N., & Palma, L. D. (2024) · Scientific Reports · doi:10.1038/s41598-024-60622-5 · Cited by 16
“Despite this limitation, the ANN may provide a powerful tool to optimize patient management 51,52 improving the inherent characteristics and quality of data.”
MethodJinad, R., Islam, A. R., & Shashidhar, N. K. (2024) · Electronics · doi:10.3390/electronics13132438 · Cited by 21
Machine learning enables electrical resistivity modeling of printed lines in aerosol jet 3D printing
Li, M., Yin, S., Liu, Z., & Zhang, H. (2024) · Scientific Reports · doi:10.1038/s41598-024-65693-y · Cited by 15
“However, as the interpretability of features in deep convolutional layers is an area of ongoing research, directly interpreting these features, especially those extracted from deeper layers, needs more analysis in future research work 49,50 .”
BackgroundThe Role of Uncertainty Quantification for Trustworthy AI
Deuschel, J., Foltyn, A., Roscher, K., & Scheele, S. (2024) · Springer eBooks · doi:10.1007/978-3-031-64832-8_5 · Cited by 27
Zou, J., Wang, C., Chen, S., Zhang, J., Bing, Q., & Yang, H. (2024) · Sustainable Cities and Society · doi:10.1016/j.scs.2024.105885 · Cited by 16
Artificial intelligence improves risk prediction in cardiovascular disease
Teshale, A. B., Htun, H. L., Vered, M., Owen, A. J., Ryan, J. L., Tonkin, A. M., & Freak‐Poli, R. (2024) · GeroScience · doi:10.1007/s11357-024-01438-z · Cited by 18
“This highlights the significance of incorporating explainable AI (XAI) approaches when considering AI models [17].”
Automated Text Scoring in the Age of Generative AI for the GPU-poor
Ormerod, C. M., & Kwako, A. (2024) · Chinese/English Journal of Educational Measurement and Evaluation · doi:10.59863/okuu1904 · Cited by 24
Chen, J., Gu, Y., Zhu, Q., Gu, Y., Liang, X., & Ma, J. (2025) · Langmuir · doi:10.1021/acs.langmuir.4c04638 · Cited by 14
Qureshi, U. R., Rashid, A., Altini, N., Bevilacqua, V., & Scala, M. L. (2025) · Electronics · doi:10.3390/electronics14040755 · Cited by 19
“Broadly, XAI methods are categorized into two complementary approaches [71–73]: perceptive explainability and mathematical interpretability.”
Zhao, J., Han, C., Wu, Y., Xu, C., Huang, X., Qi, X., Qi, Y., & Gao, L. (2025) · Environmental Impact Assessment Review · doi:10.1016/j.eiar.2025.107862 · Cited by 18
Ethical considerations in AI-based user profiling for knowledge management: A critical review
Njiru, D. K., Mugo, D. M., & Musyoka, F. M. (2025) · Telematics and Informatics Reports · doi:10.1016/j.teler.2025.100205 · Cited by 20
“Adadi et al. (2018) analysed 381 papers on explainable AI and noted that while 47 % of the studies recognized the importance of interpretability, only 5 % proposed concrete methods for achieving it in complex models [9,10].”
Edris, E. K. K. (2025) · Electronics · doi:10.3390/electronics14102057 · Cited by 18
Rahman, M. M., Calhoun, V. D., & Plis, S. (2026) · Imaging Neuroscience · doi:10.1162/imag.a.1129 · Cited by 16
Schober, S. A., Bahri, Y., Carbonelli, C., & Wille, R. (2022) · Chemosensors · doi:10.3390/chemosensors10050152 · Cited by 14
On Using Explainable Artificial Intelligence for Failure Identification in Microwave Networks
Ayoub, O., Musumeci, F., Ezzeddine, F., Passera, C., & Tornatore, M. (2022) · Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN) · doi:10.1109/icin53892.2022.9758095 · Cited by 17
Local Explanations of Global Rankings: Insights for Competitive Rankings
Anahideh, H., & Mohabbati-Kalejahi, N. (2022) · IEEE Access · doi:10.1109/access.2022.3159245 · Cited by 19
“Explainability of algorithmic decision-making, especially machine learning models, has recently been a field of focus and high demand [5].”
BackgroundTowards Explainability of Tree-Based Ensemble Models. A Critical Overview
Sepioło, D., & Ligęza, A. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-06746-4_28 · Cited by 19
Trust Metrics for Medical Deep Learning Using Explainable-AI Ensemble for Time Series Classification
Siddiqui, K., & Doyle, T. E. (2022) · Conference proceedings - Canadian Conference on Electrical and Computer Engineering · doi:10.1109/ccece49351.2022.9918458 · Cited by 22
“Robustness deals with the concept of consistency in the AI’s decision making especially as equipment, sensors, processors, and other hardware may change, as well as human subjects that data might be gathered from [3] [4] [34] [33].”
BackgroundA DEXiRE for Extracting Propositional Rules from Neural Networks via Binarization
Contreras, V., Marini, N., Fanda, L., Manzo, G., Mualla, Y., Calbimonte, J.-P., Schumacher, M., & Calvaresi, D. (2022) · Electronics · doi:10.3390/electronics11244171 · Cited by 18
Understanding oxidation of Fe-Cr-Al alloys through explainable artificial intelligence
Roy, I., Feng, B., Roychowdhury, S., Ravi, S. K., Umretiya, R. V., Reynolds, C., Ghosh, S., Rebak, R. B., & Hoffman, A. (2023) · MRS Communications · doi:10.1557/s43579-022-00315-0 · Cited by 16
Is Generative Artificial Intelligence the Next Step Toward a Personalized Hemodialysis?
Hueso, M., Álvarez, R., Marí, D., Ribas, V. J., Lekadir, K., & Vellido, A. (2023) · Revista de investigaci�n Cl�nica · doi:10.24875/ric.23000162 · Cited by 22
“Thus, there is a concern about result interpretability for models that could have a significant impact on patients’ health that reflects the inability to explain which aspects of the dataset used in the training phase led to a predicted result 36 .”
BackgroundTowards Balancing Preference and Performance through Adaptive Personalized Explainability
Silva, A., Tambwekar, P., Schrum, M., & Gombolay, M. (2024) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3610977.3635000 · Cited by 24
“…network models that can be readily interpreted [107], pursuing natural language generation for explanations [14, 29, 72, 109], presenting feature-importance maps for input samples [13, 35, 48, 83, 101, 102, 109], presenting relevant training data [11, 12, 54, 94], and other techniques [42, 44, 67].”
Beyond the Black Box: Interpretability of LLMs in FinancePreprint
Tatsat, H., & Shater, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5263803 · Cited by 29
Integrating Automation in Biomass Transformation: Opportunities, Challenges, and Future Directions
Ananda, A., Sujeeth, R. K., & Archana, S. (2025) · BioEnergy Research · doi:10.1007/s12155-025-10864-6 · Cited by 13
“XAI techniques are typically divided into two categories: intrinsically interpretable models, such as decision trees, rule-based systems, and generalised additive models, and post hoc explanation methods that interpret decisions made by more complex models [139].”
A Review of Artificial Intelligence-Driven Active Vibration and Noise Control
Jiang, Z., Xue, H., Yue, H., Bao, X., Zhu, J., Wang, X., & Zhang, L. (2025) · Machines · doi:10.3390/machines13100946 · Cited by 19
“In recent years, explainable artificial intelligence (XAI) has become a key requirement for establishing trustworthy AI control strategies [228], especially in safety-critical engineering applications, where learned control strategies need to have explainable mechanisms, verifiable stability and…”
Trustworthy AI in education: Framework, cases, and governance strategies
Ma, Y., Li, X., Hu, S., Liu, S., & Cheong, K. H. (2025) · Innovation and Emerging Technologies · doi:10.1142/s2737599425500264 · Cited by 16
Gonçalves, A., & Correia, A. C. (2025) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp6010007 · Cited by 21
Yeboah, M. K., & Söffker, D. (2026) · Bioresources and Bioproducts · doi:10.3390/bioresourbioprod2010004 · Cited by 14
“These studies also emphasize the importance of rigorous training/validation/test separation to obtain unbiased performance estimates on unseen CBP scenarios [89,119].”
InfluentialSketchXAI: A First Look at Explainability for Human Sketches
Qu, Z., Gryaditskaya, Y., Li, K., Pang, K., Xiang, T., & Song, Y.-Z. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02234 · Cited by 28
“XAI research to date has focused on two modalities: photo [15,38,49,88] and text [16,39,42,66,76].”
BackgroundIIoT System for Intelligent Detection of Bottleneck in Manufacturing Lines
Aguilar, M. J. R., Abad, I., & Cerrada, J. A. (2023) · Applied Sciences · doi:10.3390/app14010323 · Cited by 13
Mu, B., Zhao, Z.-J., Yuan, S., Qin, B., Dai, G., & Zhou, G.-B. (2024) · Atmospheric Research · doi:10.1016/j.atmosres.2024.107306 · Cited by 13
Explainable AI: Machine Learning Interpretation in Blackcurrant Powders
Przybył, K. (2024) · Sensors · doi:10.3390/s24103198 · Cited by 16
“The Local Interpretable Model-agnostic Explanations (LIME) technique was used to discuss the explainability of the model relative to texture features [30,35,36].”
BackgroundMethodNeural network-driven interpretability analysis for evaluating compressive stress in polymer foams
SANCHEZ, A. E. R., Plascencia‐Mora, H., & Acevedo-Alvarado, M. (2024) · Journal of Cellular Plastics · doi:10.1177/0021955x241255102 · Cited by 13
“Interpretability techniques have become crucial in machine learning, 35,36 especially for regression models based on neural networks.”
BackgroundJin, Y., Li, W., Wu, Y., Wang, Q., Xiang, Z., Long, Z., Liang, H., Zou, J., Zhu, Z., & Dai, X. (2024) · International Journal of Surgery · doi:10.1097/js9.0000000000001764 · Cited by 13
“It provides interpretation to our established model, and can contribute to apply the model in clinical practice [38] .”
Gokhale, G., Madahi, S. S. K., Claessens, B., & Develder, C. (2024) · ACM International Conference on Future Energy Systems (e-Energy) · doi:10.1145/3632775.3661937 · Cited by 25
“We refer to more exhaustive reviews [24, 29] of available techniques, metrics, and methodologies across different fields such as image recognition, natural language processing, etc.”
MethodTertiary Review on Explainable Artificial Intelligence: Where Do We Stand?
van Mourik, F., Jutte, A., Berendse, S. E., Bukhsh, F. A., & Ahmed, F. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6030098 · Cited by 19
Metadata
- Authors
- Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S.
- Affiliations
- University of Patras (GR)
- Corresponding author
- Linardatos, Pantelis
- Venue
- Entropy
- Publisher
- MDPI AG
- Published
- 2020-12-25
- Volume
- 23
- Issue
- 1
- Pages
- 18
- ISSN
- 1099-4300 (ISSN-L)
- PMC
- PMC7824368
- OpenAlex
- W3116286104
- Cited by
- 2,922
- References
- 162
- Citations by year
- 2026: 485 · 2025: 702 · 2024: 701 · 2023: 565 · 2022: 370 · 2021: 97 · 2020: 1
- FWCI
- 8.89
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Entropy (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- explainable AI, model interpretability, black-box models, medical applications
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.