Factual and Counterfactual Explanations for Black Box Decision Making
Open accessThe DOI matches its Crossref record; 12 of the 14 references it cites were found in a registry or an index.
Abstract
The rise of sophisticated machine learning models has brought accurate but obscure decision systems, which hide their logic, thus undermining transparency, trust, and the adoption of artificial intelligence (AI) in socially sensitive and safety-critical contexts. We introduce a local rule-based explanation method, providing faithful explanations of the decision made by a black box classifier on a specific instance. The proposed method first learns an interpretable, local classifier on a synthetic neighborhood of the instance under investigation, generated by a genetic algorithm. Then, it derives from the interpretable classifier an explanation consisting of a decision rule, explaining the factual reasons of the decision, and a set of counterfactuals, suggesting the changes in the instance features that would lead to a different outcome. Experimental results show that the proposed method outperforms existing approaches in terms of the quality of the explanations and of the accuracy in mimicking the black box.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
"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
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
Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · cited 1×
“We also evaluate the rule coverage, namely the fraction of instances to explain covered by the rule: large values of coverage means better rule generalization.(4) Figure 8 also shows the average coverage of the decision rules, with LORE showing a consistently better coverage than ANCHOR.”
Counterfactual explanations without opening the black box: automated decisions and the GDPR
Wachter, S., Mittelstadt, B., & Russell, C. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3063289 · Cited by 1,061
Evolutionary Computation 1: Basic Algorithms and Operators
(2018) · CRC Press eBooks · doi:10.1201/9781482268713 · Cited by 634
A Survey of Methods for Explaining Black Box Models
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019) · ACM Computing Surveys · doi:10.1145/3236009 · Cited by 629
Self-citationEvolutionary Computation 2: Advanced Algorithms and Operators
(2000) · Taylor & Francis eBooks · doi:10.1201/9781420034349 · Cited by 451
A review of instance selection methods
Olvera-López, J. A., Carrasco-Ochoa, J. A., Martínez-Trinidad, J. F., & Kittler, J. (2010) · Artificial Intelligence Review · doi:10.1007/s10462-010-9165-y · Cited by 394 · cited 1×
“This task differs from approaches to instance selection based on genetic algorithms.(7) In our case, we cannot assume the availability of the training set of b, or not even that b is a supervised ML predictor for which a training set exists.”
MethodCounterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning
Byrne, R. M. J. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/876 · Cited by 285 · cited 1×
“the cognitive psychology literature maintaining that counterfactuals help people to reason on explanations that identify cause-effect or reason-action relations between events.(5,6) Similarly, Grover et al.”
BackgroundA Survey on Evolutionary Instance Selection and Generation
Derrac, J., García, S., & Herrera, F. (2010) · International Journal of Applied Metaheuristic Computing · doi:10.4018/jamc.2010102604 · Cited by 75 · cited 1×
“Our task is instead similar to instance generation in the field of active learning, including evolutionary approaches.(8) We adopt an approach based on a genetic algorithm, which generates z 2 Z1⁄4 [ Z61⁄4 by maximizing the following fitness functions:”
Method
Cited by
Items 301–400 of 438
Clustering and Explainable AI for Supporting Energy Contracting in the Brazilian Free Energy Market
Júnior, S., Matz, G. S., Paula, M. B. S., Guarnier, E., Filho, D. S., Melo, R. L., Picarelli, L. B., Rosa, V. C. V., Liang, Z., & Tinós, R. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00060 · Cited by 2
“Specifically, this study applies LOcal Rule-based Explanation (LORE) [9], an XAI technique, to provide rule-based explanations for machine learning model predictions and to present counterfactual scenarios showing how alternative inputs influence classification results.”
Wu, Z., Zou, X., Chen, Y., Zhu, Y., Yan, Q., & Ma, W. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.111694 · Cited by 2
Rule-Based Explanations for Retrieval-Augmented LLM Systems
Rorseth, J., Godfrey, P., Golab, L., Srivastava, D., & Szlichta, J. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10737-z · Cited by 2
Explainable AI for Deep Visual Recognition: Evaluation, Methods, and Open Challenges
Alharbi, K. N. (2026) · Electronics · doi:10.3390/electronics15143222 · Cited by 2
Maruf, S., Zukerman, I., Reiter, E., & Haffari, G. (2021) · International Conference on Natural Language Generation · doi:10.18653/v1/2021.inlg-1.12 · Cited by 2
“A DT’s prediction is generally explained by tracing the path from the root to a predicted outcome (Guidotti et al., 2019; Stepin et al., 2020).”
BackgroundDeclarative Reasoning on Explanations Using Constraint Logic Programming
State, L., Ruggieri, S., & Turini, F. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43619-2_10 · Cited by 2
Self-citationFLocalX - Local to Global Fuzzy Explanations for Black Box Classifiers
Fernández, G., Guidotti, R., Giannotti, F., Setzu, M., Aledo, J. A., Gámez, J. A., & Puerta, J. M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-58553-1_16 · Cited by 2
Self-citationAnalogical Classifier as a Surrogate for Explanations
Lim, S., Prade, H. M., & Richard, G. (2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia240582 · Cited by 2
UGCE: User-Guided Incremental Counterfactual Exploration
Fragkathoulas, C., & Pitoura, E. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229277 · Cited by 2
“Various methods optimize counterfactual search using genetic algorithms (GAs) [16], [32], [33], integer programming [34], [35], [37], and cost-based heuristics [36], assuming a static feasibility space.”
Use of Fitness Sharing in the Local Rule-Based Explanations Method
Santos, D. A., Baranauskas, J. A., & Tinós, R. (2021) · IEEE Latin American Conference on Computational Intelligence (LA-CCI) · doi:10.1109/la-cci48322.2021.9769789 · Cited by 2
Rule-based Explainable Artificial Intelligence
Akyol, S. (2023) · doi:10.59287/pcse.356 · Cited by 2
Wang, M., Wang, D., Wu, W., Feng, S., & Zhang, Y. (2026) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.18166 · Cited by 2
“CEs are also used in various ML-based systems [13, 14, 15, 16, 17, 18, 19] and has garnered considerable attention within various ML communities[20, 10, 21, 22, 23, 24, 25, 26].”
MethodAdvancing Edge Artificial Intelligence
Vermesan, O., & Marples, D. (2023) · doi:10.13052/rp-9788770041010 · Cited by 2
TESTING ARTIFICIAL INTELLIGENCE-BASED SOFTWARE SYSTEMS
Chandrasekaran, J. (2021) · Cited by 2
Guzey, I., Uçar, Ö., Çiftdemir, N. A., & Acunaş, B. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.08821 · Cited by 2
“[23] Guidotti R, Monreale A, Giannotti F, Pedreschi D, Ruggieri S, Turini F.”
BackgroundMethodXie, R., Chen, J., Jiang, L., Xiao, R., Pan, Y., & Cai, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.07306 · Cited by 2
Navigating the Structured What-If Spaces: Counterfactual Generation via Structured DiffusionPreprint
Madaan, N., & Bedathur, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.13616 · Cited by 2
“For the tabular domain, various studies have pursued counterfactual explanations [6], [7], [9], [33], [34].”
BackgroundRanking Counterfactual ExplanationsPreprint
Lim, S., Prade, H. M., & Richard, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.15817 · Cited by 2
“This definition is quite classical and exactly corresponds to abductive explanations as formally described in Ignatiev et al. [2019b], Amgoud et al. [2024], Ignatiev et al. [2019a], Marques-Silva et al. [2021], Guidotti et al. [2019]).”
Bobek, S., Bałec, Ł., & Nalepa, G. J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.20236 · Cited by 2
“This group can be further divided into endogenous explainers, which provide explanations by selecting existing samples from the given dataset (such as LUX [6], LORE [18]), and exogenous explainers, which generate artificial samples such as DACE [19], OCEAN [27], or PPCF [35].”
Some representation learning tasks and the inspection of their models
Pfahler, L. (2022) · Technische Universität Dortmund Eldorado (Technische Universität Dortmund) · doi:10.17877/de290r-23015 · Cited by 2
Yang, Q., Sharma, A., Calin, D., de Crecy, C., Inampudi, R., & Yin, R. G. (2025) · medRxiv · doi:10.1101/2025.03.07.25323577 · Cited by 2
“Drawing on the principles of factual and counterfactual reasoning detailed in existing works 16–18 , we developed Factual and Counterfactual Learning Networks (FCFNets) that integrates both learning paradigms.”
Foundations of machine learning interpretability
Lopardo, G. (2024) · theses.fr (ABES) · doi:10.70675/c3f1d6c7z53e2z4638z827dz4afa2d01dadc · Cited by 2
Generation of Rule-Based Explanations of CNN Classifiers Using Regional Features
Philipp, W., Yashwanthika, R., Sikha, O. K., & Benítez, R. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11678-x · Cited by 1
“Rule extraction techniques aim to create a collection of rules that capture the decision-making process of deep learning models [13].”
Biases, Fairness, and Non-discrimination
Schedl, M., Anelli, V. W., & Lex, E. (2024) · The information retrieval series · doi:10.1007/978-3-031-69978-8_3 · Cited by 1
FLARE: Fuzzy Local Agnostic Rule-Based Explanations for Closed Box Classifiers
Fernández, G., Aledo, J. A., Gámez, J. A., & Puerta, J. M. (2025) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2025.3547875 · Cited by 1
“On the other hand, LORE [10] is an agnostic method for generating both factual and counterfactual explanations by employing a decision tree as the surrogate model.”
InfluentialEvolutionary Bias Identification with Embeddings
Buzelin, A., Aquino, Y., Estanislau, V., Bento, P., Dayrell, L., Malaquias, S., Santana, C., Evangelista, G. H. G., Grossi, C. S., Rigueira, P. B., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-90065-5_21 · Cited by 1
Guo, C., Liu, H., & Guo, J. (2025) · Journal of Psychology in Africa · doi:10.32604/jpa.2025.065763 · Cited by 1
“…increases employees’ job insecurity and thus their self-protection by adopting knowledge-hiding behaviours, which inspires managers to use (at least partially) transparent algorithmic models and features to implement algorithm-based prediction and classification solutions (Guidotti et al., 2019).”
Counterfactual linguistic rule-based explanations based on locally relevant causal mechanisms
Zhang, T., & Wagner, C. (2025) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz62266.2025.11152069 · Cited by 1
“Counterfactual (CF) explanations provide a potentially powerful mechanism to deliver meaningful explanations of AI decisions [1]–[3].”
CFIRE: A General Method for Combining Local Explanations
Müller, S., Toborek, V., Horváth, T., & Bauckhage, C. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08324-1_1 · Cited by 1
AutoXAI: a meta-learning approach for recommendation of explanation techniques
Shawi, R. E., & Jamel, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-25872-x · Cited by 1
“Quantitative evaluation emphasizes metrics such as fidelity 22 and stability 23 , which measure the ability of explainers to mimic model behavior and provide consistent outputs.”
A Feasibility Study of Literature-Guided HRV Stratification Using Large Language Models
Hsu, T. Y., Tang, G.-J., Wu, C.-H., Lee, J.-T., & Kuo, T. B. J. (2026) · Diagnostics · doi:10.3390/diagnostics16040540 · Cited by 1
Giovannoni, C., Metta, C., Berti, A., Colantonio, S., Monreale, A., Pratesi, F., & Rinzivillo, S. (2026) · Machine-mediated learning · doi:10.1007/s10994-026-07033-x · Cited by 1
“Techniques such as LIME (Ribeiro et al., 2016 ), LORE (Guidotti et al., 2019 ) and Grad-CAM (Selvaraju et al., 2017) have been successfully applied in the healthcare domain.”
Self-citationInterpretable and Efficient Counterfactual Generation with Disentangled Variational Autoencoders
Barbera, C., & Passerini, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-25305-7_12 · Cited by 1
Explainable AI and Robots for Children: Why Transparency Alone is Not Enough
Yadollahi, E. (2026) · ACM International Conference on Interaction Design and Children (IDC) · doi:10.1145/3773077.3812171 · Cited by 1
“Existing work on explainable AI often treats explainability as a property of the model, focusing on making the internal processes interpretable [1, 12].”
Globally Valid Rule‐Based Explanations for Black‐Box Models
Huynh, V. Q. P., Beck, F., Küng, J., & Fürnkranz, J. (2026) · Computational Intelligence · doi:10.1111/coin.70278 · Cited by 1
Causal Post-hoc XAI: Categorisation and Systematic Literature Review
Bjøru, A. R., Langseth, H., Strümke, I., & Bach, K. (2026) · Machine Learning · doi:10.1007/s10994-026-07103-0 · Cited by 1
Fusion of fuzzy rule-based factual and counterfactual explanations with large language models
Perez-Ferreiro, P. M., Alonso, J. M., Catalá, A., & Bugarín, A. (2026) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2026.109828 · Cited by 1
Towards Reliable Machine Learning
Nisticò, S. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-42941-5_56 · Cited by 1
Cirino, F. R. P., Maia, C. D., Balbino, M. D. S., & Nobre, C. N. (2023) · doi:10.5753/kdmile.2023.232900 · Cited by 1
Schedl, M., Anelli, V. W., & Lex, E. (2024) · The information retrieval series · doi:10.1007/978-3-031-69978-8_4 · Cited by 1
Schedl, M., Anelli, V. W., & Lex, E. (2024) · The information retrieval series · doi:10.1007/978-3-031-69978-8_2 · Cited by 1
Explainability in Machine Learning: Preliminaries and Overview
Leofante, F., & Wicker, M. (2025) · SpringerBriefs in intelligent systems · doi:10.1007/978-3-031-89022-2_2 · Cited by 1
Generating Simple, Conservative and Unifying Explanations for Logistic Regression Models
Maruf, S., Zukerman, I., Situ, X., Paris, C. L., & Haffari, G. (2024) · International Conference on Natural Language Generation · doi:10.18653/v1/2024.inlg-main.9 · Cited by 1
“These components have strong support in the eXplainable Artificial Intelligence ( XAI ) literature (Biran and McKeown, 2017; Guidotti et al., 2019; Maruf et al., 2023; Miller, 2019; Sokol and Flach, 2020; Stepin et al., 2020; van der Waa et al., 2018).”
BackgroundSun, Y., Wang, T., & Rudin, C. D. (2024) · neural information processing systems · doi:10.52202/079017-0827 · Cited by 1
Opening the black box: a primer for anti-discrimination
Ruggieri, S., Giannotti, F., Guidotti, R., Monreale, A., Pedreschi, D., & Turini, F. (2020) · CINECA IRIS Institutial research information system (University of Pisa) · Cited by 1
Self-citationAdapting by copying. Towards a sustainable machine learning
Unceta, I. (2021) · Dipòsit Digital de la Universitat de Barcelona (Universitat de Barcelona) · Cited by 1
Rizzi, W., Francescomarino, C. D., Ghidini, C., & Maggi, F. M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.14939 · Cited by 1
“Counterfactual explanations, obtained by adapting counterfactual explainers such as DiCE [41] and LORE [42] are instead investigated in [38] and [39], respectively.”
BackgroundHow to Measure Human-AI Prediction Accuracy in Explainable AI SystemsPreprint
Koujalgi, S., Anderson, A. W., Adenuga, I. J., Soneji, S., Dikkala, R., Nader, T. G., Soccio, L., Panda, S., Das, R. K., Burnett, M., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.00069 · Cited by 1
“LORE [29] generates a decision tree classifier for input instances in the area around an AI system’s particular decision.”
MethodAI for ESG Governance in South Africa: A Systematic Review of Financial Intelligence ApproachesPreprint
Mathebula, M., Modupe, A., Marivate, V. N., & du Toit, E. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5443142 · Cited by 1
Counterfactual optimization for fault prevention in complex wind energy systemsPreprint
Carrizosa, E., Fischetti, M., Haaker, R., & Morales, J. M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.08849 · Cited by 1
“…optimization techniques, as seen in [2], [7], [13], and [14]; multi-objective optimization strategies, as discussed in [3], [4], and [18]; robust optimization approaches, like those in [17]; SAT-based methods, e.g., [13]; and heuristic and metaheuristic techniques, as explored in [10].”
Löfström, H. (2023) · Jönköping University Publications (Jönköping University) · Cited by 1
CounterFlowNet: From Minimal Changes to Meaningful Counterfactual ExplanationsPreprint
Furman, O., Marszałek, P., Masłowski, J., Gaiński, P., Zieba, M., & Śmieja, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.17244 · Cited by 1
“Their value is particularly pronounced in sensitive tabular domains such as finance, healthcare, and legal decision-making, where understanding both model behavior and plausible counter-factual scenarios is critical (Zhou et al., 2023; Guidotti et al., 2019).”
Chawla, A. (2022) · Research@THEA · Cited by 1
Parekh, J. (2023) · theses.fr (ABES) · doi:10.70675/4a87c674ze676z494czb250zd2ef86b5cb76 · Cited by 1
Explainable algorithms for anomaly detection and time series forecasting
Kong, L. (2024) · theses.fr (ABES) · doi:10.70675/f3f56534zcb22z4c9fzb5fez6b38e2066740 · Cited by 1
Génération d'explications post-hoc personnalisées
Jeyasothy, A. (2024) · theses.fr (ABES) · doi:10.70675/b1aff9a7z7fe2z4d6azab5bzb45d1d6a851f · Cited by 1
Alonso, J. M., & Cortés, U. (2020) · Repositorio institucional da Universidade de Santiago de Compostela (University of Santiago de Compostela)
Explaining Explanation Methods.
Guidotti, R. (2020) · CINECA IRIS Institutial research information system (University of Pisa)
Self-citationExploiting auto-encoders for explaining black-box classifiers
Guidotti, R. (2022) · Intelligenza Artificiale · doi:10.3233/ia-220139
“We propose llore , a Latent LOcal Rule-based Explainer based on lore [25]. llore is a local, post-hoc, model-agnostic, and data-agnostic explanation framework able to overcome the limitations of existing approaches by exploiting the latent feature space, learned through different types of…”
InfluentialSelf-citationOCEANUI: INTERFACE PARA GERAÇÃO DE EXPLICAÇÕES CONTRAFACTUAIS
PEREIRA, M. H. (2022) · doi:10.17771/pucrio.acad.60289
Privacy Risk of Global Explainers
Naretto, F., Monreale, A., & Giannotti, F. (2022) · Frontiers in artificial intelligence and applications · doi:10.3233/faia220206
Self-citationIndução de árvore de decisão utilizando meta-aprendizado
Ferreira, C. A. (2022) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.59.2022.tde-05122022-145141
“Por meio dos estudos realizados na área [1, 3, 5, 6, 9, 11, 14], caracterizam-se alguns critérios para avaliar os resulta-dos produzidos pelo Aprendizado de Máquina.”
BackgroundUser tests & techniques for the post-hoc explanation of deep learning
Delaney, E. D., Kenny, E. M., Greene, D., & Keane, M. T. (2023) · Elsevier eBooks · doi:10.1016/b978-0-32-396098-4.00019-3
Indução de Árvore de Decisão utilizando Meta-Aprendizado
Ferreira, C. A., & Baranauskas, J. A. (2023) · Brazilian Symposium on Multimedia and the Web · doi:10.5753/webmedia_estendido.2023.233232
Punzi, C., Maslennikova, A., Gezici, G., Pellungrini, R., & Giannotti, F. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44067-0_31
Self-citationdos Santos, D. A. (2022) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.59.2022.tde-17112023-112559
Fernández, G., Gámez, J. A., Puerta, J. M., Aledo, J. A., Alonso, J. M., & Bugarín, A. (2024) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee60900.2024.10611812
“Factual explanations [16], [17] are a common type of local explanations, which can be defined as an answer to the question about why a particular instance is classified into a certain class value.”
BackgroundConclusions and Open Challenges
Schedl, M., Anelli, V. W., & Lex, E. (2024) · The information retrieval series · doi:10.1007/978-3-031-69978-8_6
Schedl, M., Anelli, V. W., & Lex, E. (2024) · The information retrieval series · doi:10.1007/978-3-031-69978-8_5
Schedl, M., Anelli, V. W., & Lex, E. (2024) · The information retrieval series · doi:10.1007/978-3-031-69978-8_1
Danese, D., Noia, T. D., Lombardi, A., Lofù, D., Nazary, F., Sardone, R., & Sorino, P. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-75110-3_7
ExplainReduce: Summarising local explanations via proxiesPreprint
Seppäläinen, L., Guo, M., & Puolamäki, K. (2025) · arXiv.org · doi:10.48550/arxiv.2502.10311
An Interpretable Hypergraph Model for Resume-Job Matching Decision making
Shen, D., Hu, C., Jiang, X., Xu, S., Wang, H., Zhang, Z., Yao, F., & Wang, T. (2025) · International Conference on Computer Technology Applications (ICCTA) · doi:10.1109/iccta65425.2025.11166402
“(2) To obtain interpretable model results, we design a generator for node subsets that considers both factual and counterfactual inference objectives [3].”
Tilia: Enhancing LIME with Decision Tree Surrogates
Li, J., Qiu, J., Zhao, Y., & Wen, Z. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761130
“Among existing explanation techniques, Local Interpretable Model-Agnostic Explanations (LIME) [27] remains widely used [26] as both a foundational method [20, 40] and a standard comparative baseline [5, 15, 17, 37, 45].”
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
An Axiomatic Approach to Explainable Artificial Intelligence.
Hashemi, M. (2025) · UNSWorks (UNSW Sydney) · doi:10.26190/unsworks/31212
Unsupervised scene graph retrieval using graph autoencoders
Chaidos, N. (2024) · DSpace - NTUA (National Technical University of Athens) · doi:10.26240/heal.ntua.26887
Visual Representation of Explainable Artificial Intelligence Methods: Design and Empirical Studies
Martínez, M. A. M. (2023) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000164577
Learning and explainable system for decision support in production control
Theumer, P., Reinhart, G., & München, T. U. (2024)
Saveri, G. (2025) · Electronic Theses and Dissertations Repository (University of Pisa)
Pivotal Instances Identification for Learning Interpretable Decision-Making Models
Cascione, A. (2024) · Electronic Theses and Dissertations Repository (University of Pisa)
Opening the Black Box: Empowering Machine Learning Models with Explanations
Setzu, M. (2022) · Electronic Theses and Dissertations Repository (University of Pisa)
Causality without Estimands: from Causal Estimation to Black-Box Introspection
Parafita, Á. (2023) · Tesis Doctorals en Xarxa (Consorci de Serveis Universitaris de Catalunya)
Explainable ML for drug prediction
Gonzalez, D. D.-R. (2024) · DiVA (Linkoping University)
Rezaie, J., Maslesa, A., & Curbi, A. (2025) · Lund University Publications Student Papers (Lund University)
AI explanations: Do they benefit everyone? A case study of image classifiersPreprint
Kim, H. K., Park, H., & Park, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5527616
Challenges and Risks to the Inclusion of AI for Environmental Applications
Aleksandrova, I., & Milshina, Y. (2026) · Springer eBooks · doi:10.1007/978-981-95-3767-9_10
Investigação da radiação natural na praia de Meaípe (ES) utilizando rede neural
Gigi, M. M. (2025) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.14.2025.tde-05012026-045955
Balbino, M. D. S., Nobre, C. N. , & 2023-09-19 (2023) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)
ALIME: Local Interpretable Explanations based on Generalized Additive Models
Wang, Y., Dong, Y., Liang, H., Li, Y., Wu, Y., & Zha, Q. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343193
“Guidotti et al. [14] adopted the decision tree model to replace the linear model in the original LIME, expanding the output form to decision rules and counterfactual rules.”
Memory Retrieval in Transformers: Insights from The Encoding Specificity PrinciplePreprint
Dinh, V. H., Ding, M., Qu, Y., & Thilakarathna, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.20282
“…in transformer LLMs using various techniques, including input perturbation (Fong & Vedaldi, 2017), surrogate models (Ribeiro et al., 2016; Guidotti et al., 2019; Leemann et al., 2025), gradient-based methods (Simonyan et al., 2014; Shriku-mar et al., 2017; Lundberg & Lee, 2017), and…”
Interpretable and Constrained Machine Learning via Combinatorial Optimization
Shati, P. (2025) · TSpace (University of Toronto)
ReasonX: Declarative Reasoning on ExplanationsPreprint
State, L., Ruggieri, S., & Turini, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.23810
Self-citationA software architecture for verifiable and explainable classification
Barbosa, R., Rinzivillo, S., Robin, J., Beretta, A., & Madeira, H. (2026) · Machine Learning · doi:10.1007/s10994-026-07006-0
“4) of the counterfactual, we use an explainer that produces factual and counterfactual logical rules (Guidotti et al., 2019).”
49915 Interpretierbare und erklärbare KI
Fürnkranz, J. (2026) · doi:10.1515/9783111386690-018
Bergamin, L. (n.d.) · Padua Research Archive (University of Padova)
Li, W., Li, S., Zhao, X., Lai, M., Cascarano, P., & Marfia, G. (2026) · IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) · doi:10.1109/vrw70859.2026.00099
“[7].”
Generating Explanatory Rules for Temporal Data Using Prior Knowledge
Cappuccio, E., Kathirgamanathan, B., Rinzivillo, S., Andrienko, G., & Andrienko, N. V. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-25308-8_29
Halaswamy, D., Kantha, L., Giridhara Naidu, B., Rakesh, N., Muthukrishnan, K. B., & Kantayya, R. (2025) · IEEE International Conference on Recent Trends in Computing and Smart Mobility (RCSM) · doi:10.1109/rcsm67767.2025.11508026
Metadata
- Authors
- Guidotti, R., Monreale, A., Giannotti, F., Pedreschi, D., Ruggieri, S., & Turini, F.
- Affiliations
- Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" (IT)
- University of Pisa (IT)
- ORCID
- Venue
- IEEE Intelligent Systems
- Published
- 2019-11-01
- Volume
- 34
- Issue
- 6
- Pages
- 14-23
- ISSN
- 1541-1672 (ISSN-L)
- 1941-1294
- OpenAlex
- W2994120362
- Cited by
- 349
- References
- 14
- Citations by year
- 2026: 38 · 2025: 67 · 2024: 62 · 2023: 60 · 2022: 47 · 2021: 48 · 2020: 26 · 2019: 1
- FWCI
- 13.92
- Type
- journal article
- Language
- en
- Open access
- green
- ieeexplore.ieee.org
- Licence
- Locations
- IEEE Intelligent Systems (publishedVersion)
- CINECA IRIS Institutial research information system (University of Pisa) (submittedVersion, other-oa)
- ISTI Open Portal (submittedVersion, other-oa)
- Scuola Normale Superiore di Pisa (submittedVersion)
- Funders
- European Commission (INFRAIA-1-2014-2015)
- 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 › Information Systems › Data Mining Algorithms and Applications
- Keywords
- explainable AI, black-box classifiers, counterfactual explanations, genetic algorithm, interpretable classifiers, model transparency, trust in AI
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.