Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics
Open accessThe DOI matches its Crossref record; 88 of the 88 references it cites were found in a registry or an index.
Abstract
The most successful Machine Learning (ML) systems remain complex black boxes to end-users, and even experts are often unable to understand the rationale behind their decisions. The lack of transparency of such systems can have severe consequences or poor uses of limited valuable resources in medical diagnosis, financial decision-making, and in other high-stake domains. Therefore, the issue of ML explanation has experienced a surge in interest from the research community to application domains. While numerous explanation methods have been explored, there is a need for evaluations to quantify the quality of explanation methods to determine whether and to what extent the offered explainability achieves the defined objective, and compare available explanation methods and suggest the best explanation from the comparison for a specific task. This survey paper presents a comprehensive overview of methods proposed in the current literature for the evaluation of ML explanations. We identify properties of explainability from the review of definitions of explainability. The identified properties of explainability are used as objectives that evaluation metrics should achieve. The survey found that the quantitative metrics for both model-based and example-based explanations are primarily used to evaluate the parsimony/simplicity of interpretability, while the quantitative metrics for attribution-based explanations are primarily used to evaluate the soundness of fidelity of explainability. The survey also demonstrated that subjective measures, such as trust and confidence, have been embraced as the focal point for the human-centered evaluation of explainable systems. The paper concludes that the evaluation of ML explanations is a multidisciplinary research topic. It is also not possible to define an implementation of evaluation metrics, which can be applied to all explanation methods.
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
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 cited source says what the claim attributes to it.
In the citing paper
“They found that some properties (clarity, broadness, and completeness) are still in shortage of appropriate metrics, and so is the class of explanations that are example-based.”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [141]
In the citing paper
“It is not possible to come up with quantitative metrics that are applicable for all interpretability methods [169].”
From Transparency of deep neural networks for medical image analysis: A review of interpretability methods (2022) · cites this paper as [169]
In the citing paper
“They conclude their survey by stating that”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [141]
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
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 2×
“One way to objectively evaluate explanations is to verify whether the explanation mechanism satisfies (or does not satisfy) certain axioms, or properties [34].”
Background"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
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 1×
“[39] explained an ensemble of models, such as neural networks with a single model effectively.”
BackgroundCausality: Models, Reasoning, and Inference
Pearl, J. (2009) · doi:10.1017/cbo9780511803161 · Cited by 11,653
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“Explanation is also a domain-specific note, and there cannot be an all-purpose explanation [22], and different types of explanations might be useful.”
BackgroundPeeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294 · cited 2×
“The machine learning explainability has been reviewed thoroughly in recent years [10,14,17,23,28,31,32].”
BackgroundLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087 · cited 4×
“…Main effect complexity [46] Level of (dis)agreement [82] Attribution-based explanations Monotonicity [80] Non-sensitivity [80,83], Sensitivity [84,85] Effective complexity [80] Remove and retrain [86] Recall of important features [33] Implementation invariance [85] Selectivity [87] Continuity…”
BackgroundInfluentialTowards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121 · cited 4×
“The advantages of application-grounded and human-grounded evaluations are that they can provide direct and strong evidence of success of explanations [9].”
BackgroundMethodInfluential
Research works printed but not linked: 5
- Zhou, J., and Chen, F. (2018). Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent, Springer.
- Lage, I., and Doshi-Velez, F. (2020, January 17). Human-in-the-Loop Learning of Interpretable and Intuitive Representations. Proceedings of the ICML Workshop on Human Interpretability in Machine Learning, Vienna, Austria.
- Becker, B., Kohavi, R., and Sommerfield, D. (2001). Visualizing the Simple Bayesian Classifier. Information Visualization in Data Mining and Knowledge Discovery, Morgan Kaufmann Publishers Inc.
- Poursabzi-Sangdeh, F., Goldstein, D.G., Hofman, J.M., Vaughan, J.W., and Wallach, H. (2019). Manipulating and Measuring Model Interpretability. arXiv.
- Yang, M., and Kim, B. (2019). Benchmarking Attribution Methods with Relative Feature Importance. arXiv, 1907.
Cited by
Items 501–600 of 676
Explainable Deep Learning Models for Healthcare Decision Support
(2023) · International Journal of Advances in Computer Science and Technology · doi:10.30534/ijacst/2023/0112102023 · Cited by 4
“Additionally, healthcare workers appreciate EDLMs that support group decision-making[23].”
An Explainable Enterprise Credit Evaluation Method Based on Logistic Regression Integration
Zhai, B., Wang, F., Xie, Z., & Song, S. (2024) · International Conference on Economic Management and Big Data Application (ICEMBDA) · doi:10.4108/eai.27-10-2023.2341908 · Cited by 1
Cognitive Computing in Smart Cities and Healthcare
Mahadevprasad, V. D., Rudhra, O., & Singh, S. K. (2024) · Wiley eBooks · doi:10.1002/9781394214068.ch16 · Cited by 2
Based on the RFE-LSTM Ozone Prediction Research
Ji, W., Ren, G., Han, M., & Lin, H. L. (2024) · International Conference on Electronic Technology and Information Science (ICETIS) · doi:10.1109/icetis61828.2024.10593779 · Cited by 1
“These metrics are widely used in the fields of statistics and machine learning as they reflect the magnitude of the discrepancy between the model's predicted values and the actual values, serving as important indicators for assessing the model's predictive performance [7] .”
DeepSVM-A Novel Approach for Early Detection and Classification of IoT Botnet Attacks
Antony, V., & Thangarasu, N. (2024) · International Conference on Inventive Computing and Informatics (ICICI) · doi:10.1109/icici62254.2024.00035 · Cited by 1
“More than 3800 large organizations suffered from data breaches in 2019 that had disastrous outcomes, according to the Outpost24 report [3].”
BackgroundDecoupled and Explainable Associative Memory for Effective Knowledge Propagation
Fernando, T., Priyasad, D., Sridharan, S., & Fookes, C. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3492133 · Cited by 2
“Based on [32], explanation approaches in machine learning can be divided into three categories: 1) model-based explanations: a simple, new model is used to explain the complex original model; 2) attribute-based explanations: ranks or measures the importance or influence of input features to the…”
A Human-Centered Multiperspective and Interactive Visual Tool For Explainable Machine Learning
Lopes, B. G. C. O., Soares, L. S., Gonçalves, M. A., & Prates, R. O. (2025) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2025.3982 · Cited by 1
“In some works, authors make an explicit distinction between them 1 , whereas in others, these concepts are used interchangeably and sometimes even considered syn-onymous [Mohseni et al ., 2021; Vilone and Longo, 2021; Zhou et al ., 2021; Cao et al ., 2024].”
Utilization of Machine Learning in Breast Cancer Detection
Momani, M., Yousef, N., Aljawazneh, Q. S., Issa, A., Abuowaida, S. F. A., Alazaidah, R., Khouj, M., Batyha, R. M., & Elsoud, E. A. (2024) · International Arab Conference on Information Technology (ACIT) · doi:10.1109/acit62805.2024.10877058 · Cited by 1
Wieben, A. M., Steege, L. M. B., Brown, R., & Gilmore‐Bykovskyi, A. L. (2025) · CIN Computers Informatics Nursing · doi:10.1097/cin.0000000000001323 · Cited by 1
Nie, X., & Ahmad, F. (2025) · Future Technology · doi:10.55670/fpll.futech.4.4.2 · Cited by 1
Mahlau, Y., & Nolde, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.01565 · Cited by 1
“As a result, various metrics for measuring fidelity have been developed [41].”
BackgroundA Trustworthy View on XAI Method EvaluationPreprint
LI, D., Liu, Y., Huang, J., & Wang, Z. (2022) · doi:10.36227/techrxiv.21067438.v2 · Cited by 2
Predicting SSH keys in Open SSH Memory dumpsPreprint
Rascoussier, F. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.16838 · Cited by 1
Alrusaini, O. A., & Beyari, H. (2024) · Research Square · doi:10.21203/rs.3.rs-5030218/v1 · Cited by 1
Elia, M., Lopez, A. M., Páez, K. A. C., Bauer, B., & García-Cuesta, E. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5149144 · Cited by 1
Achieving Explainable, Scalable, and Robust Machine Learning for Real-World ApplicationsPreprint
Nuan, Y., & Ru, Z. (2025) · Preprints.org · doi:10.20944/preprints202506.2515.v1 · Cited by 1
Cardozo, S., Montero, G., Kazhdan, D., Dimanov, B., Wijaya, M., Jamnik, M., & Lio, P. (2022) · arXiv (Cornell University) · doi:10.17863/cam.95333 · Cited by 1
From black box to glass box: algorithmic explainability as a strategic decisionPreprint
Raizonville, A., & Lambin, X. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3958902 · Cited by 1
Long range thermal image object recognition for perimeter security
Mihaescu, R. E., Carata, S.-V., Chindea, M., & Ghenescu, M. T. (2022) · International Conference on Communications (COMM) · doi:10.1109/comm54429.2022.9817184
Ribeiro, J. M., & Roque, L. (2022) · Aerospace · doi:10.3390/aerospace9120754
Determine the Undervalued US Major League Baseball Players with Machine Learning
Xiong, L., Tian, K., Qian, Y., Musyoka, W., & Chen, X. (2023) · International Journal of Innovative Technology and Exploring Engineering · doi:10.35940/ijitee.b9406.0212323
(2023) · Computer · doi:10.1109/mc.2023.3254040
Mogaraju, J. K. (2023) · Air Quality Atmosphere & Health · doi:10.1007/s11869-023-01366-5
“Though the true nature of the computations is kept concealed or hidden, it is always important to check the evaluation metrics periodically for the efficiency of the models trained for a purpose (Zhou et al. 2021).”
BackgroundAnalysis of chemical composition of ancient glass products based on random forest
Yang, J., Xue, H., Chen, J., & Zhang, J. (2023) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit59027.2023.10212541
Pesecan, C.-M., & Stoicu-Tivadar, L. (2023) · Studies in health technology and informatics · doi:10.3233/shti230807
Rojas-López, A. G., Uriarte-Arcia, A. V., Rodríguez-Molina, A., & Villarreal-Cervantes, M. G. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-45316-8_25
Nasarian, E., Alizadehsani, R., Acharya, U. R., & Tsui, K. (2023) · Research Square · doi:10.21203/rs.3.rs-3626164/v1
Kroeun, K. (2023) · International Journal of Science and Research (IJSR) · doi:10.21275/sr23918222004
Explaining Taxi Demand Prediction Models Based on Feature Importance
Loff, E., Schleibaum, S., Müller, J. P., & Säfken, B. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-50396-2_15
Kricfalusi, M., Rice, R. C., Cabrera, A., Dasari, P., Chung, D., Case, T. R., Ruckle, D., Liu, J. N., Cheng, W. K., & Danisa, O. (2024) · International Journal of Research in Orthopaedics · doi:10.18203/issn.2455-4510.intjresorthop20240402
Aggarwal, A., Puri, C., ADITYA, A., RAVIKANT, R., & Kumar, N. K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4766770
Zitar, R. A., Aljasmi, A., Seghrouchni, A. E. F., & Barbaresco, F. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-66336-9_27
Cambodian Secondary English Private School Students' Attitudes Toward English Public Speaking ClassPreprint
Kroeun, K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4964472
A qualitative investigation of explanation goodness in a biomedical AI system
Johs, A. J., Weber, R. O., & Agosto, D. E. (2024) · iDEA - Drexel University Institutional Repository · doi:10.17918/00010668 · Cited by 1
Risk prediction of endocrine diseases using data science and explainable artificial intelligence
Ketata, F. (2024) · theses.fr (ABES) · doi:10.70675/f9d5ea05z8aa8z43c8z94ebz1ad6436aea26 · Cited by 1
Mohammadi, A., Soleimani, A., & Parvin, S. (2024) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon62879.2024.10754751
Using artificial neural network to find problematic data and improve fuzzy models
Kudłacik, P. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.09.441
Design and Development of Artificial General Intelligence for Power System Operation
Raghuraman, S., Aakash, B., Kabilan, D., Kameswaran, A., & Suria Deepan, P. (2024) · International Conference on Power, Energy, Control and Transmission Systems (ICPECTS) · doi:10.1109/icpects62210.2024.10780272
“It is crucial when the cost of FP is high [12 - 13].”
InfluentialA formal corpus of mathematical theorems: a bridge from natural language to first-order logic
Li, L., Li, Z., Hu, P., & Zhang, H. (2024) · International Conference on Computing and Pattern Recognition (ICCPR) · doi:10.1145/3704323.3704363
“The corpus is also used to validate and test existing systems and algorithms by comparing system outputs with standard answers, evaluating performance and accuracy, identifying shortcomings, and making optimizations[19].”
Implementation of Point-Based Scoring Model for Fraud Detection
Lhymn, S. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825865
Arifin, F., & Wicaksono, A. (2025) · BIO Web of Conferences · doi:10.1051/bioconf/202515707007
“Model evaluation in machine learning is very much needed, this is because evaluation aims to measure how well the model works with the data that has been given [21].”
Sushma, S., & Singh, H. (2024) · International Conference on System Modeling & Advancement in Research Trends (SMART) · doi:10.1109/smart63812.2024.10882491
“To assess the effectiveness of our machine learning algorithm, we took metrics from the appropriate data such as accuracy, precision, recall, and F-Measure [31]. metrics from the appropriate data such as accuracy precision, recall, and F-Measure [31].”
Smart Diagnosis Using Symptoms for Seeking a Specialist Doctor
Das, B., & Kumar, R. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-81935-3_5
Towards Resilient AI Models for Wireless Networks From Highly Scarce Data
Qureshi, H. N., & Imran, M. A. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901836
“Many recent survey papers focus on making NN resilient to data size and data errors by making them more interpretable [5], [6], [7], [8], [9], [10].”
Fabris, V. L., de Oliveira, J. R., Silva, C. H. B., Cassenote, V., da Silva, J. V. N. A., Arrais, R. R., & Paris, R. D. (2024) · doi:10.5753/eniac.2024.245025
Evaluating Sensitivity Consistency of Explanations
Tan, H. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00028
“The most popular approach is feature removing [44], based on the idea that eliminating features with the highest attribution in the explanations would severely disrupt predictions.”
Machine Learning-Based Approach to Predict Liver Disease Using an Imbalanced Dataset
Ahosan, A. B., Uddin, K. M. M., Islam, F., Janin, F. T., & Based, M. A. (2024) · IEEE International Conference on Biomedical Engineering, Computer and Information Technology for Health (BECITHCON) · doi:10.1109/becithcon64160.2024.10962687
A Comparative Study of Probabilistic and Ensemble Learning for Liver Disease Diagnosis
Hassoon, I. M. (2025) · Iraqi Journal of Science · doi:10.24996/ijs.2025.66.4.25
“It is simple, fast, and obtains high performance [7].”
Research and Development of Kubernetes Operator for Machine Learning Pipelines
Trapezin, A., & Filianin, I. (2025) · International Russian Smart Industry Conference (SmartIndustryCon) · doi:10.1109/smartindustrycon65166.2025.10985995
“Consequently, the task is to build a unified control loop capable of acting on the basis of data on model versions and objective metrics of their quality [10-12], providing automated commissioning of machine learning solutions with specified indicators of reliability, scalability and predictability.”
Hybrid Optimized Deep Learning Rna-Seq Achromatopsia Detection for Biomarker DiscoveryPreprint
Abdelaziz, A., & Ead, W. M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5251944
Shaikh, M. A., Ismail, M., Bakhsh, P., Jokhio, S., Khan, M. A., & Ali, K. (2025) · VFAST Transactions on Software Engineering · doi:10.21015/vtse.v13i2.2103
Practical Guidelines for Building Explainable, Efficient, and Robust Machine Learning SystemsPreprint
Zheng, H., & Ru, Z. (2025) · doi:10.31224/4744
Duric, A., Tørresen, J., Riegler, M. A., & Hammer, H. L. (2025) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms65348.2025.00125
Enhancing Breast Cancer Detection: A Multi-model Approach
Katta, S. S. S., Singh, V., Jena, J. J., Gourisaria, M. K., & Bilgaiyan, S. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-2182-8_53
Developing Explainable Approximating Representation for Intelligent Transportation Systems
Németh, B., & Gáspár, P. (2025) · Mediterranean Conference on Control and Automation (MED) · doi:10.1109/med64031.2025.11073211
“Open issues with explainable methods are formalism of explanations, assessing the quality of explanations, and effective methods for measuring them [12].”
Navigating Metrics: Maximizing Research Impact in Academic Publishing
Deb, R., Deb, M., & Sengar, G. S. (2024) · Trends in Scholarly Publishing · doi:10.21124/tsp.2024.10.13
Lavrič, M., & Lavrič, A. L. (2025) · Mednarodno inovativno poslovanje = Journal of Innovative Business and Management · doi:10.32015/jibm.2025.17.1.8 · Cited by 1
Artificial Nudging: Improving Policy Outcomes with AI TransparencyPreprint
Carroll, B. J., Burke, P. F., & Zhou, J. J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5386642
Self-citationExploring Ensemble Methods for Spam Classification
Shashikala, Y., Satyasri, R., Shaheena, S., Uppalapati, P. J., Karunasri, A., & Kumari, K. R. (2025) · Springer proceedings in mathematics & statistics · doi:10.1007/978-3-031-84517-8_38
Emotion Classification in Digital Art using Color Features and Machine Learning
Igor, E., Toganas, N., & Shamoi, P. (2025) · IEEE International Conference on Smart Information Systems and Technologies (SIST) · doi:10.1109/sist61657.2025.11139293 · Cited by 2
“It shows the counts of true positives, false positives, true negatives, and false negatives, offering insights into where the model succeeds and where it errs [38].”
AI in Analyzing Audience Responses to Contemporary Graphic Design
Shaway, A. M., & Mohsen, B. M. (2025) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi65310.2025.11141134
“Zhou et al. (2021) In Their Paper [10] deal with the quality assessment of ML explanations, a central problem in explaining ML models and their predictions.”
The Role of Artificial Intelligence in Analyzing the Performance of Iraqi Theatrical Actors
Khazal, K. K. (2025) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi65310.2025.11141262
“Furthermore, Zhou et al. [13] analyzed quality of explanations given by AI when used for machine learning models, which provide insights into the extent of interpretability with AI used for performance assessments.”
Fundamentals of machine learning
Mustafa, K., Rezakazemi, M., & Mahboob, R. M. M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-27422-0.00010-4
X-Ray Fluorescence for Geological Samples Combined with Chemometrics
Roy, A. (2025) · Springer eBooks · doi:10.1007/978-3-031-98375-7_12
Corte, T. D., Verhaeghe, J., Ongenae, F., Waele, J. J. D., & Hoecke, S. V. (2025) · Applied Sciences · doi:10.3390/app152010933
User-centered Method for Explaining Autonomous Vehicle Control Systems via Decision Trees
Németh, B., Kopasz, M., Hegedűs, T., & Gáspár, P. (2025) · European Control Conference (ECC) · doi:10.23919/ecc65951.2025.11186928
“In the last couple of years, significant research has been completed to understand the properties, qualitatively and quantitatively define metrics [14].”
Sentiment Mining on Movie Reviews using Natural Language Processing to Analyze Audience Reactions
Fuyuhang, Husin, H. S. B., Marjani, M., Mohamad, A. H., & Erfina, A. (2025) · International Conference on Metaverse and Current Trends in Computing (ICMCTC) · doi:10.1109/icmctc62214.2025.11196309
“Recent research [19-20] shows that the LSTM model is significantly better than traditional machine learning methods in analyzing movie review sentiment.”
Enhancing Predictive Accuracy in Aircraft Engine MRO using Clustering and Similarity Methods
Mendonça, L., Pires, F., Barbosa, J., Duarte, M., & Leitão, P. (2025) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa65518.2025.11205599
“However, even with meticulous data preparation, there is no guarantee that a ML model will be robust [1], as the evaluation metrics alone are often insufficient to ensure that the model accurately reflects the complexities of operations and processes [5].”
Training Resilient AI Models With Rich Interpretations From Highly Scarce Data
Qureshi, H. N., & Imran, M. A. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3627389
“Surrogate models , sometimes referred to as proxy models in [17] or knowledge distillation methods in [29] first learn a simpler model, to approximate a complex model [24], [26], [28].”
InfluentialRobot Delivery of Actionable Counterfactual Neural Network Explanations: Results in Group Perception
Narcomey, A., Claure, H., & Vázquez, M. (2025) · IEEE RO-MAN · doi:10.1109/ro-man63969.2025.11217869
“Prior work surveying properties of effective ML explanation methods [49] highlights the importance of high fidelity in describing model behavior alongside simplicity and easy interpretability by people.”
A Practical Framework for Auditing Fairness in Medical AI
Oprescu, A. M., Vindel-Alfageme, J., Campos-Espinosa, E., Caro-Martínez, M., Díaz-Agudo, B., Ternero, M. D. C. R., & Recio-García, J. A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-10489-2_23
Using Closed Frequent Itemsets To Explain Classification Tasks
Ngo, T., & Le, B. H. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-10209-6_22
Abidin, D. Z., Siswanto, A., Saputra, C., Betantiyo, B., & Toscany, A. N. (2025) · Jurnal Teknik Informatika (Jutif) · doi:10.52436/1.jutif.2025.6.5.5177
Fraud Detection in Financial Transactions Using Ensemble Machine Learning Models
Michael, O., Odeh, C., Maduabuchuku, A., Nwakeze, O. M., Love., E.-O. C., & Akachukwu, O. C. (2025) · International journal of research and scientific innovation · doi:10.51244/ijrsi.2025.1213cs006
Moradisani, H., Zarrinkalam, F., Noorian, Z., & Ensan, F. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11421-5
EXP-CAM: Explanation Generation and Circuit Discovery Using Classifier Activation MatchingPreprint
Suhail, P., Anand, A., & Sethi, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.25686
Ali, F. A. R., Ahmed, S. A., Hasan, M. S., Sahi, S., Samir, M., Mahmod, S. A., & Ahmed, J. M. (2025) · International Conference on Cyber Resilience (ICCR) · doi:10.1109/iccr67387.2025.11292208
Εφαρμογές τεχνητής νοημοσύνης για την βελτίωση της ποιότητας ζωής σε ασθενείς με ́άνοια
Avgerinos, P. (2025) · DSpace - NTUA (National Technical University of Athens) · doi:10.26240/heal.ntua.28750
Tailoring Data Storage Configuration for Efficient Fraud Detection Model Training
Syarif, A., Putra, M. H., & Gabteni, H. (2025) · Selamat Datang di Repository UAD (Universitas Ahmad Dahlan) · doi:10.26555/jiteki.v10i4.30013
Cambodian Secondary English Private School Students' Attitudes Toward English Public Speaking Class
Kroeun, K. (2023) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.8386401
González, A. M. L. (2024) · Archivo Digital UPM (Universidad Politécnica de Madrid)
Operationalizing Transparency and Explainability in Artificial Intelligence through Standardization
Tamminen, P. (2022) · UTUPub (University of Turku) · Cited by 4
Trustworthy enough? Evaluation of an AI decision support system for healthcare professionals
Kacafírková, K. S. (2023) · VUBIR (Vrije Universiteit Brussel) · Cited by 3
Cardozo, S., I., M. G., Kazhdan, D., Dimanov, B., Wijaya, M., Jamnik, M., & Lio, P. (2022) · IRIS Research product catalog (Sapienza University of Rome)
Börresen, H., & Mykhalevych, K. (2024) · DiVA (Linnaeus University) · Cited by 1
Ransomware Resilience: A Real-time Detection Framework using Kafka and Machine Learning
Khan, S., Hussain, R. M., Baig, T. S., & Qasim, M. M. (2024) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/2024617081
Research Group Critical Information Infrastructures (cii), Sunyaev, A., Sturm, B., Du, G., Schmidt-Kraepelin, M., Kannengießer, N., Toussaint, P. A., Thiebes, S., & Heß, Y. (2025) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000185402
Makkena, K. R., & Natarajan, K. (2025) · Information systems engineering and management · doi:10.1007/978-3-031-97709-1_28
A Benchmarking Blueprint for Ontology-Based Information Retrieval in Large-Scale Knowledge Systems
Sassi, N. (2025) · IEEE Access · doi:10.1109/access.2025.3648942
“Semantic search aims to retrieve by meaning rather than surface form, aligning results to intent, context, and conceptual relations [33], [90].”
Rubric-Guided Evaluation Framework for Consistent Scoring with Large Language Models
Anghel, C., Crăciun, M., Pecheanu, E., Cocu, A., Istrate, A., & Anghel, A. A. (2025) · doi:10.1109/iseee67817.2025.11304842
“As highlighted in surveys on explanation methods, the ability to evaluate and compare interpretability metrics is critical for ensuring that automated assessment tools are both reliable and pedagogically meaningful [16].”
Andrès, F., Knoppers, J. V. T., & Dhungana, S. R. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-2235-3.ch006
Ilmi, N. A., & Winarsih, N. A. S. (2025) · Journal of Applied Informatics and Computing · doi:10.30871/jaic.v9i6.11272
“Meanwhile, in agnostic models, techniques such as SHAP (Shapley Additive Explanations) provide an assessment of the marginal contribution of each feature to the final prediction, accounting for feature interactions [22].”
Fernandes, E. C. (2023) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)
Musyaffi, A. M., Prihartini, R., Ikhwan, M., Sudiati, R., Armeliza, D., Adha, M. A., & Maychella, M. S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-13196-6_4
TWEEF: Trustworthiness Estimation and Enhancement Framework for Machine Learning Models
Ugalde, J., Salas, R., Torres, R., Velandia, D., Bariviera, A. F., Estévez, P. A., & Godoy, M. P. (2026) · Applied Sciences · doi:10.3390/app16021077
Meza, V., & Chinchilla-Soto, C. (2026) · Revista Forestal Mesoamericana Kurú · doi:10.18845/rfmk.v23i52.8437
Narayanan, A., & Bergen, K. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.00331
“However, growing evidence indicates these techniques can produce inconsistent or unreliable explanations, with results varying across methods (Neely et al 2021; Zhou et al 2021).”
Miyaji, R. O., & Corrêa, P. L. P. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-15638-9_2
Restricted Receptive Fields for Face Verification
Öztürk, K., Bhatta, A., Wu, H., Flynn, P. J., & Bowyer, K. W. (2026) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2026.3663919
“In face recognition, convolutional neural network (CNN) representations have been e ff ectively leveraged to improve verification performance [14], [15], [16], [17], [18], [19], [20].”
Evaluating Machine Learning Models for Phishing Detection in Cybersecurity
Panthakkan, A., Anzar, S. M., Markarian, C., & Mansoor, W. (2025) · International Conference on Social Networks Analysis, Management and Security (SNAMS) · doi:10.1109/snams67467.2025.11391188
Metadata
- Authors
- Zhou, J., Gandomi, A. H., Chen, F., & Holzinger, A.
- Affiliations
- University of Technology Sydney (AU)
- Medical University of Graz (AT)
- Corresponding author
- Zhou, Jianlong
- Gandomi, Amir H.
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2021-03-04
- Volume
- 10
- Issue
- 5
- Pages
- 593
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W3133543405
- Cited by
- 606
- References
- 80
- Citations by year
- 2026: 75 · 2025: 138 · 2024: 179 · 2023: 109 · 2022: 84 · 2021: 20
- FWCI
- 34.65
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- OPUS - Open Publications of UTS Scholars (University of Technology Sydney) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- University of Technology Sydney
- Austrian Science Fund (P 32554)
- 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 machine learning, explanation quality evaluation, evaluation metrics, explainability, model-based explanation, example-based explanations, interpretability, fidelity, human-centered evaluation, black-box models
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.