Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Open accessThe DOI matches its Crossref record; 168 of the 181 references it cites were found in a registry or an index, and 10 are not checked yet; 20 of the 74 sources its claims cite were checked for support.
Abstract
This review surveys explainable AI, emphasizing transparency, interpretability, trust, and evaluation across high-stakes domains.
Verified 2026-11-20 · 10 references not checked yet
Overview
CoChat Summary
## TL;DR
This paper is a survey of explainable artificial intelligence (XAI) that organizes the field around why XAI is needed, how explanations are produced, and where the main challenges lie. It argues that black-box AI systems need explainability for trust, accountability, regulation, and safer deployment across domains such as healthcare, finance, and transportation.
## Key findings
- The review proposes a revised hierarchical taxonomy for XAI and says it is intended to serve as a building block for future researchers.
- It distinguishes two broad interpretability classes: perceptive interpretability and interpretability by mathematical structures; it also separates explanations by scope (global vs. local) and by stage (ante hoc vs. post hoc).
- The paper summarizes model-agnostic methods such as PDP, ICE, ALE, LIME, and counterfactuals, and reports their main trade-offs; for example, PDP is intuitive but valid for at most three features, ICE can become unreadable due to overcrowding, and ALE is described as unbiased for correlated features and faster to compute.
- In the paper’s escitalopram example, the interpretable version of the model achieved approximately 70% accuracy in identifying patients more likely to benefit from the treatment.
- It also notes a reported example where CrystalCandle explanations increased a LinkedIn software sales team’s subscription revenue by 8%.
## Methods
- Narrative review / survey of XAI literature; the authors state that they “careful[ly]” selected and analyzed current state-of-the-art XAI research.
- The paper synthesizes prior work into a taxonomy and organizes the discussion into conceptual background, need for XAI, evaluation frameworks, challenges, discussion/reflection, and future directions.
- The analysis is qualitative and comparative, using cited examples from multiple application domains and explaining the strengths and weaknesses of different explanation methods.
## Limitations
- The paper states that a “thorough and systematic survey is still lacking despite the large number of surveys” in the area, which indicates the field remains fragmented.
- It explicitly says XAI is still in its infancy and that a more formal approach is needed to address diverse user questions; it also notes that guidelines alone do not guarantee success.
- Evident from the text: no new datasets were generated or analyzed in this study, so the conclusions are based on literature synthesis rather than original empirical testing.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
15 Valid · 25 Not valid · 49 Not checked · 59 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“With the aim of providing an explanation for legal judgment predictions generated by Legal Judgement Prediction (LJP), Zhong et al. [71] designed the QAjudge.”
§ Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence > Need For Reasoning
What the sources say
- Supportedcites [71] 71. Zhong H, Wang Y, Tu C, Zhang T, Liu Z, Sun M. Iteratively questioning and answering for interpretable legal judgment prediction. In: Proceedings of the AAAI Conference on Arti- ficial Intelligence, vol. 34. 01 ed. 2020. p. 1250-7. https:// ojs. aaai. org/ index. php/ AAAI/ artic le/ view/ 5479. source
The Abstract (p. 1) states QAjudge is 'a model based on reinforcement learning to visualize the prediction process and give interpretable judgments' for Legal Judgment Prediction, and the Conclusion (p. 7) reiterates that QAjudge is proposed 'to provide interpretable results for LJP' addressing the lack of interpretability in existing LJP methods. The Introduction (p. 2) likewise frames the goal as detecting elements so that professionals and non-specialists can understand the prediction results. Thus the attribution — that Zhong et al. designed QAjudge to explain/interpret LJP predictions — is directly stated in our copy. (LLM, conf=0.90)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Additionally, by exposing the system to contradictory examples where the same symptoms can indicate different diseases, the system can learn to evaluate multiple possibilities and make a more accurate diagnosis [91].”
§ Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence > Contradictions Provide Alternative Approaches
What the sources say
- Could not verifycites [91] 91. Chou YL, Moreira C, Bruza P, Ouyang C, Jorge J. Counterfac- tuals and causability in explainable artificial intelligence: The- ory, algorithms, and applications. Inf Fusion. 2022;81:59-83. sourceExperimental — accuracy not yet measured
Section 7 (p. 39) discusses counterfactual explanations in medical decision support, and Section 8.1 (p. 42) discusses questions a clinician might ask about a patient's fever. Neither says that exposing a diagnostic system to examples in which the same symptoms indicate different diseases helps it consider alternatives or improve diagnostic accuracy. Searches for contradictory symptom examples and diagnostic accuracy found no passage addressing that claim. (LLM, conf=0.73)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“HCI skills such as philosophy, psychology, and cognitive science have proven their worth in the field of XAI by developing explanations that were able to stimulate the human explanation process [89].”
§ Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence > Collaborative Techniques Should Be Implemented More
What the sources say
- Partly supportedcites [89] 89. Miller T. Explanation in artificial intelligence: Insights from the social sciences. Artif Intell. 2019;267:1-38. https:// www. scien cedir ect. com/ scien ce/ artic le/ pii/ S0004 37021 83059 88. sourceExperimental — accuracy not yet measured
The Introduction says research in philosophy, psychology, and cognitive science offers valuable insights into how humans explain, and §5.3.2 describes an interactive XAI system that tailored explanations to users. But the paper does not say these fields have already proven their worth by developing explanations that stimulate the human explanation process: the Introduction says most XAI work has not built on social-science frameworks, and §5.3.6 says recent XAI has not truly adopted socially interactive explanation. (LLM, conf=0.84)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Distillation turns out to be a more effective method for obtaining interpretable models.”
§ Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence > Model Extraction
What the sources say
- Could not verifycites [102] Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. 2015. https://arxiv.org/abs/1503.02531. sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes distillation as transferring knowledge to a smaller model suited to deployment, and the Discussion (p. 8) says the resulting model is easier to deploy. Neither passage addresses whether distilled models are more interpretable; a search for interpretability and interpretable models found no passage making that comparison. (LLM, conf=0.74)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
In the paper
“The chart (Fig. 5) shows that IUD has the least proportional interaction effect with other variables compared to years of using hormonal contraception [107].”
§ Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence > Feature Interaction
What the sources say
- Not matchedcites [107] Molnar C. Interpretable Machine Learning. 2nd ed. 2022. https://christophm.github.io/interpretable-ml-book.
We searched by its title and found no matching paper.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
27 more claims
Create a free account to see all 148 claims and to verify the 21 references still open.
- Probably not a substantial claim. 108
- It may state two separate claims as one. 37
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
“For safety-critical systems, explainability is not enough for a system to be trustworthy.Various requirements such as robustness, reliability, traceability, data quality, and other factors must be demonstrated [25,43,62,63].”
From A requirements model for AI algorithms in functional safety-critical systems with an explainable self-enforcing network from a developer perspective (2024) · cites this paper as [43]
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
“Furthermore, users' primary focus is usually on obtaining the desired outcome efficiently, prioritizing resolution over understanding of why a failure occurred (Collier et al., 2017;Hassija et al., 2024).”
From Explainability in AI: Comparing Human-Like and System-Like Trust Repair Strategies (2026) · cites this paper as Hassija et al., 2024
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
“By revealing the conditions under which the CA succeeds or fails, XAI-based strategies transform an unpredictable black-box AI system into a more comprehensible one, helping users evaluate whether to continue interacting with the CA despite having experienced an error (Hassija et al., 2024;Zhao et al., 2024).”
From Explainability in AI: Comparing Human-Like and System-Like Trust Repair Strategies (2026) · cites this paper as Hassija et al., 2024
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
“Unfortunately, AI does not provide explanations for its decisions, often termed a ‘Black-Box Model’; thus, adopting such models in sensitive decisions such as research retraction is difficult.50”
From Artificial Intelligence in Detecting Statistical Errors: Implications for Authors, Reviewers, and Editors (2025) · cites this paper as [50]
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
“The results from this study support prior studies demonstrating that organizations will lose trust in “black box” AI systems until they implement explainability mechanisms and auditability controls (Buhrmester et al. 2021; Hassija et al. 2024).”
From AI-driven financial fraud detection in Pakistan’s banking sector: bridging strategic intent and operational implementation (2026) · cites this paper as Hassija et al. 2024
Experimental — accuracy not yet measured
2 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.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence > Human-Machine Collaboration
“Figure 14 shows the benefit of AI in the workplace, according to the survey.”
§ Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence > Responsible AI
“To ensure that the design and development of responsible AI reflect the ethical concerns of humans, we propose to incorporate the above-discussed factors with the principles proposed by Dignum [185], i.e., accountability, responsibility, and transparency (ART) as depicted in Fig. 14.”
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“One of the noteworthy methods is the permutation feature importance (PFI) by Breiman [108] for random forests.”
MethodImageNet 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×
“Human beings have been defeated for the first time in related open challenges [3] (e.g., ImageNet image-classification [4], COCO object-detection [5]) since the introduction of AlexNet [6].”
BackgroundMicrosoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
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 1×
“Some of the popularly implemented visualisation techniques are: Partial dependence plot (PDP) uses graph-based explanations for visualising the relationship between one or more features (at maximum three features) and the prediction generated by the black-box model [130].”
MethodGrad-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
"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 · cited 5×
“To develop local explanations for black-box models, Ribeiro et al. introduced the Local Interpretable Model-Agnostic explanation (LIME) [34].”
BackgroundMethodInfluentialMastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · cited 1×
“One of the significant milestones was witnessed in 2016 when an AI player AlphaGo [9, 10], was able to defeat the human world champion Sedol Lee in a game of Go.”
BackgroundDistilling 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×
“Hinton et al. [102] proposed transparent model distillation, a unified technique for model extraction, which was used to tackle the above-stated issue.”
MethodLearning 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
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321 · cited 2×
“Existing surveys [21–24] focus on answering “What, Why, and How” to encompass all aspects of XAI.”
BackgroundBarredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423 · cited 2×
“Existing surveys [21–24] focus on answering “What, Why, and How” to encompass all aspects of XAI.”
BackgroundExplaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
A working guide to boosted regression trees
Elith, J., Leathwick, J. R., & Hastie, T. (2008) · Journal of Animal Ecology · doi:10.1111/j.1365-2656.2008.01390.x · Cited by 6,484 · cited 1×
“…effects of predictors on the conditional average treatment outcome derived from a voter mobilisation experiment, Green and Kern [131] Elith et al. [132] made major contributions outside of the research area by replacing stochastic gradient boosting with PDP to comprehend how different…”
MethodPeeking 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
The global landscape of AI ethics guidelines
Jobin, A., Ienca, M., & Vayena, E. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0088-2 · Cited by 6,220 · cited 1×
“On the basis of three components of the Independent High-Level Expert Group on AI (LEG), an algorithm can be said to be ethical [87].”
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
The Mythos of Model Interpretability
Lipton, Z. C. (2016) · arXiv · doi:10.48550/arxiv.1606.03490 · Cited by 5,422
Explanation in Artificial Intelligence: Insights from the Social Sciences
Miller, T. (2017) · arXiv · doi:10.48550/arxiv.1706.07269 · Cited by 5,338
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 · cited 1×
“HCI skills such as philosophy, psychology, and cognitive science have proven their worth in the field of XAI by developing explanations that were able to stimulate the human explanation process [89].”
BackgroundVQA: Visual Question Answering
Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C. L., & Parikh, D. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.279 · Cited by 4,487
Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
Breiman, L. (2001) · Statistical Science · doi:10.1214/ss/1009213726 · Cited by 4,340 · cited 1×
“However, accuracy suffers as a result of this intrinsic interpretability [128].”
BackgroundTowards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Artificial intelligence and the future of work: Human-AI symbiosis in organizational decision making
Jarrahi, M. H. (2018) · Business Horizons · doi:10.1016/j.bushor.2018.03.007 · Cited by 2,772 · cited 1×
“Although these machines can surpass humans in terms of data processing [178], they lack accountability and interpretability and hence are referred to as “black boxes.””
BackgroundA Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI
Tjoa, E., & Guan, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3027314 · Cited by 2,524 · cited 2×
“Tjoa et al. [39] proposed two major classes of interpretability, i.e., perceptive interpretability and interpretability by mathematical structures.”
BackgroundExplaining prediction models and individual predictions with feature contributions
Štrumbelj, E., & Kononenko, I. (2014) · Knowledge and Information Systems · doi:10.1007/s10115-013-0679-x · Cited by 2,286 · cited 1×
“They used the preliminary information available from the work proposed by Štrumbelj and Kononenko [117] to design a new set of values called the expectation Shapley (ES) values which were able to unify and justify a broad spectrum of approaches (e.g., LIME, DeepLift, and Layer-Wise Rel-evance…”
MethodExplainability for artificial intelligence in healthcare: a multidisciplinary perspective
the Precise4Q consortium, Amann, J., Blasimme, A., Vayena, E., Frey, D., & Madai, V. I. (2020) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-020-01332-6 · Cited by 2,203
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×
“An extension of LIME can be found in anchors [112] proposed by the same creators.”
BackgroundKNN Model-Based Approach in Classification
Guo, G., Wang, H., Bell, D., Bi, Y., & Greer, K. (2003) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-39964-3_62 · Cited by 2,099 · cited 1×
“The explanation is based on the principle that the algorithm classifies a new data point based on the class labels of its nearest neighbos in the training dataset [125].”
BackgroundGoldstein, A., Kapelner, A., Bleich, J., & Pitkin, E. (2015) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2014.907095 · Cited by 1,861 · cited 1×
“Goldstein et al. supported the same [133].”
Adversarial Examples: Attacks and Defenses for Deep Learning
Yuan, X., He, P., Zhu, Q., & Li, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2886017 · Cited by 1,733
Visualizing the effects of predictor variables in black box supervised learning models
Apley, D. W., & Zhu, J. (2020) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/rssb.12377 · Cited by 1,535 · cited 1×
“Zhu [137], ALE plots are always the forerunner when it comes to visualising features that are correlated.”
BackgroundExplainable artificial intelligence (XAI) in deep learning-based medical image analysis
van der Velden, B. H. M., Kuijf, H. J., Gilhuijs, K. G. A., & Viergever, M. A. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102470 · Cited by 1,328
Predictive learning via rule ensembles
Friedman, J. H., & Popescu, B. E. (2008) · The Annals of Applied Statistics · doi:10.1214/07-aoas148 · Cited by 1,315 · cited 1×
“Freidman established the H-statistic and discovered a mechanism to gauge the strength of feature interaction [106].”
BackgroundGrundy, S. M., Pasternak, R., Greenland, P., Smith, S., & Fuster, V. (1999) · Circulation · doi:10.1161/01.cir.100.13.1481 · Cited by 1,315
Interpretable Machine Learning: Fundamental Principles and 10 Grand ChallengesPreprint
Rudin, C., Chen, C.-F., Chen, Z., Huang, H., Semenova, L., & Zhong, C. (2021) · Statistics Survey · doi:10.48550/arxiv.2103.11251 · Cited by 1,254
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., & Sayres, R. (2017) · arXiv · doi:10.48550/arxiv.1711.11279 · Cited by 1,240
Fisher, A., Rudin, C., & Dominici, F. (2018) · arXiv · doi:10.48550/arxiv.1801.01489 · Cited by 1,165
Evaluating the Visualization of What a Deep Neural Network Has Learned
Samek, W., Binder, A., Montavon, G., Lapuschkin, S., & Muller, K.-R. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2599820 · Cited by 1,164
Explainable artificial intelligence: A survey
Dosilovic, F. K., Brcic, M., & Hlupic, N. (2018) · 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) · doi:10.23919/mipro.2018.8400040 · Cited by 1,147 · cited 1×
“Dosilovic et al. [70]. provided a general review of XAI in their paper’s closing remarks.”
BackgroundDota 2 with Large Scale Deep Reinforcement Learning
OpenAI, :, Berner, C., Brockman, G., Chan, B., Cheung, V., Dębiak, P., Dennison, C., Farhi, D., Fischer, Q., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.06680 · Cited by 1,065 · cited 1×
“Since then, deep reinforcement learning (RL)- based programs and applications have been developed to determine the degree to which they can compete with human champion players in various games like Texas hold’em poker [11] and Dota 2 [12].”
BackgroundCounterfactual 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 · cited 1×
“Counterfactuals Counterfactual explanations were suggested by Wachter et al. [145]. as a way to explain predictions and choices made by enigmatic AI algorithms.”
BackgroundUnmasking Clever Hans predictors and assessing what machines really learn
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W., & Müller, K.-R. (2019) · Nature Communications · doi:10.1038/s41467-019-08987-4 · Cited by 1,047 · cited 1×
“To date, numerous frameworks have been proposed for achieving interpretability which justifies their work through one criterion or another [36–38].”
BackgroundAdversarial Examples Are Not Bugs, They Are Features
Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B., & Madry, A. (2019) · arXiv · doi:10.48550/arxiv.1905.02175 · Cited by 971
Interpretable machine learning: Fundamental principles and 10 grand challenges
Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., & Zhong, C. (2022) · Statistics Surveys · doi:10.1214/21-ss133 · Cited by 958
Designing Theory-Driven User-Centric Explainable AI
Wang, D., Yang, Q., Abdul, A., & Lim, B. Y. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300831 · Cited by 906
GNNExplainer: Generating Explanations for Graph Neural Networks
Ying, R., Bourgeois, D., You, J., Zitnik, M., & Leskovec, J. (2019) · arXiv · doi:10.48550/arxiv.1903.03894 · Cited by 850
Explainable artificial intelligence: an analytical review
Angelov, P. P., Soares, E. A., Jiang, R., Arnold, N. I., & Atkinson, P. M. (2021) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1424 · Cited by 843 · cited 1×
“An early survey on the matter by Angelov et al. [68] provides an analytical review of explainable artificial intelligence (XAI) methods with a focus on developing AI models that are transparent and interpretable to humans.”
BackgroundA Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems
Mohseni, S., Zarei, N., & Ragan, E. D. (2021) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3387166 · Cited by 785 · cited 1×
“Overall, the interaction of explainability with AI highlights the importance of developing AI systems that are transparent, interpretable, and trustworthy in order to ensure their responsible and effective deployment in various domains [50–52].”
BackgroundA Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems
Mohseni, S., Zarei, N., & Ragan, E. D. (2018) · arXiv · doi:10.48550/arxiv.1811.11839 · Cited by 783
Letham, B., Rudin, C., McCormick, T. H., & Madigan, D. (2015) · The Annals of Applied Statistics · doi:10.1214/15-aoas848 · Cited by 766 · cited 1×
“Letham et al. [126] proposed a model called Bayesian Rule Lists (BRL), which is based on decision trees as mentioned in [127].”
MethodAbdul, A., Vermeulen, J., Wang, D., Lim, B. Y., & Kankanhalli, M. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174156 · Cited by 743
Cross-trial prediction of treatment outcome in depression: a machine learning approach
Chekroud, A. M., Zotti, R. J., Shehzad, Z., Gueorguieva, R., Johnson, M. K., Trivedi, M. H., Cannon, T. D., Krystal, J. H., & Corlett, P. R. (2016) · The Lancet Psychiatry · doi:10.1016/s2215-0366(15)00471-x · Cited by 676 · cited 1×
“Another example of an incorrect prediction by ML that could be fixed by interpretability is the case of a deep learning model that was developed to predict which patients would benefit from an antidepressant medication called escitalopram [35].”
BackgroundA Survey Of Methods For Explaining Black Box Models
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Pedreschi, D., & Giannotti, F. (2018) · arXiv · doi:10.48550/arxiv.1802.01933 · Cited by 630
Antoniadi, A. M., Du, Y., Guendouz, Y., Wei, L., Mazo, C., Becker, B. A., & Mooney, C. (2021) · Applied Sciences · doi:10.3390/app11115088 · Cited by 629 · cited 1×
“Until now, four main areas of focus have been identified: A way to explain complex black-box models, performance and analysis of neural networks, improving the popularity of white box models among developers, and methods to eliminate discrimination and improve fairness [186].”
BackgroundA 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 · cited 1×
“Guidotti et al. [69] have conducted a comprehensive assessment of approaches for illuminating black-box models that combine machine learning and data mining.”
BackgroundSynthesizing Robust Adversarial Examples
Athalye, A., Engstrom, L., Ilyas, A., & Kwok, K. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.07397 · Cited by 625
Superhuman AI for multiplayer poker
Brown, N., & Sandholm, T. (2019) · Science · doi:10.1126/science.aay2400 · Cited by 592 · cited 1×
“Since then, deep reinforcement learning (RL)- based programs and applications have been developed to determine the degree to which they can compete with human champion players in various games like Texas hold’em poker [11] and Dota 2 [12].”
BackgroundComprehensible classification models: a position paper
Freitas, A. A. (2014) · ACM SIGKDD Explorations Newsletter · doi:10.1145/2594473.2594475 · Cited by 572 · cited 1×
“For example, decision trees are considered interpretable in many situations [162].”
BackgroundImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2014) · arXiv · doi:10.48550/arxiv.1409.0575 · Cited by 567
(2016) · neural information processing systems · Cited by 556
Machlev, R., Heistrene, L., Perl, M., Levy, K. Y., Belikov, J., Mannor, S., & Levron, Y. (2022) · Energy and AI · doi:10.1016/j.egyai.2022.100169 · Cited by 552
Visualizing and Understanding Convolutional Networks
Zeiler, M. D., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1311.2901 · Cited by 522
Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
Das, A., & Rad, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11371 · Cited by 504
Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., Shcherbina, A., & Kundaje, A. B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.01713 · Cited by 496
The multi-modal fusion in visual question answering: a review of attention mechanisms
Lu, S., Liu, M., Yin, L., Yin, Z., Liu, X., & Zheng, W. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1400 · Cited by 477 · cited 1×
“Following that, we come to the idea of responsible artificial intelligence, which is an AI that takes into account societal values as well as moral and ethical issues to improve the usability of AI models in real-world applications [27, 28].”
BackgroundComparison of feature importance measures as explanations for classification models
Saarela, M., & Jauhiainen, S. (2021) · SN Applied Sciences · doi:10.1007/s42452-021-04148-9 · Cited by 456 · cited 1×
“For some datasets and problems, this approach may provide more accurate and trustworthy explanations than other methods [110, 111].”
Deep Learning in Mining Biological Data
Mahmud, M., Kaiser, M. S., McGinnity, T. M., & Hussain, A. (2021) · Cognitive Computation · doi:10.1007/s12559-020-09773-x · Cited by 446 · cited 1×
“It is essential to note that the highly efficient predictions of AI models are derived from Deep Neural Networks (DNNs) which originate from extremely complex non-linear statistical models and innumerable parameters, thus compromising the aforementioned algorithms’ transparency [16, 17].”
BackgroundSelf-citationShin, D. (2020) · Journal of Broadcasting & Electronic Media · doi:10.1080/08838151.2020.1843357 · Cited by 414 · cited 1×
“Consumer technologies have undergone extensive research and are constructed using a number of predetermined principles, including justice, accountability, and transparency [179].”
BackgroundHolzinger, A., Carrington, A., & Müller, H. (2020) · KI - Künstliche Intelligenz · doi:10.1007/s13218-020-00636-z · Cited by 406
Towards better analysis of machine learning models: A visual analytics perspective
Liu, S., Wang, X., Liu, M., & Zhu, J. (2017) · Visual Informatics · doi:10.1016/j.visinf.2017.01.006 · Cited by 397 · cited 1×
“Examples of lossless visualisation methods include dimensionality reduction techniques [135, 136] (such as PCA or t-SNE), scatter plots, and heat maps.”
MethodToo much, too little, or just right? Ways explanations impact end users' mental models
Kulesza, T., Stumpf, S., Burnett, M., Yang, S., Kwan, I., & Wong, W.-K. (2013) · 2013 IEEE Symposium on Visual Languages and Human Centric Computing · doi:10.1109/vlhcc.2013.6645235 · Cited by 388 · cited 1×
““Too Much, Too Little, or Just Right?,” a work proposed by Kulesza et al. [182] presented their findings to reveal how explanations are impacting end users’ mental models.”
BackgroundTowards Automatic Concept-based Explanations
Ghorbani, A., Wexler, J., Zou, J., & Kim, B. (2019) · arXiv · doi:10.48550/arxiv.1902.03129 · Cited by 378
Jiang, H., Wang, M., Zhao, P., Xiao, Z., & Dustdar, S. (2021) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2021.3084251 · Cited by 345 · cited 1×
“So , along with a strong foundation, necessary amendments will always help in adding more to the structure of XAI, which will lead to a greater impact [94, 95].”
BackgroundRaghu, M., Gilmer, J., Yosinski, J., & Sohl-Dickstein, J. (2017) · arXiv · doi:10.48550/arxiv.1706.05806 · Cited by 335
Visualizing the Feature Importance for Black Box Models
Casalicchio, G., Molnar, C., & Bischl, B. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-10925-7_40 · Cited by 325 · cited 1×
“Casalicchio et al. [134]. were able to break the dilemma between PDP and ICE by proposing an approach that could use both of the visualisation tools as an aid to make black-box models transparent.”
MethodUsing Sampling and Queries to Extract Rules from Trained Neural Networks
Craven, M. W., & Shavlik, J. W. (1994) · Machine Learning Proceedings 1994 · doi:10.1016/b978-1-55860-335-6.50013-1 · Cited by 311 · cited 1×
“An approach was provided in the study by Craven et al. [96] in 1994 that entailed the iterative creation and updating of a set of rules applied across the input and output classes of the ANN until all of the target classes have been processed.”
MethodChou, Y.-L., Moreira, C., Bruza, P., Ouyang, C., & Jorge, J. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.11.003 · Cited by 302
Random Features Strengthen Graph Neural Networks
Sato, R., Yamada, M., & Kashima, H. (2021) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611976700.38 · Cited by 285 · cited 1×
“Such work is renowned for becoming the first successful investigation in the field of local approximation of GNN [114, 115].”
BackgroundMoustafa, N., Koroniotis, N., Keshk, M., Zomaya, A. Y., & Tari, Z. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3280465 · Cited by 266 · cited 1×
“While partial dependence plots result in a significantly biased computed feature effect, ALEs provide a faster and unbiased substitute for visualisation [138, 139].”
Background"What is relevant in a text document?": An interpretable machine learning approach
Arras, L., Horn, F., Montavon, G., Müller, K.-R., & Samek, W. (2017) · PLOS ONE · doi:10.1371/journal.pone.0181142 · Cited by 257 · cited 1×
“The resultant values could be in the form of probabilities (the LIME model [34]), super-pixels (ACE algorithm [40]), and heatmaps (CAM and LRP [41–45]).”
BackgroundKaur, S., Singla, J., Nkenyereye, L., Jha, S., Prashar, D., Joshi, G. P., El-Sappagh, S., Islam, M. S., & Islam, S. M. R. (2020) · IEEE Access · doi:10.1109/access.2020.3042273 · Cited by 255 · cited 1×
“One example of this statement is the development of AI-based medical diagnostic systems [90].”
BackgroundExplainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation
Zhu, J., Liapis, A., Risi, S., Bidarra, R., & Youngblood, G. M. (2018) · 2018 IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2018.8490433 · Cited by 255 · cited 1×
“Zhu et al. [88] noticed that instead of focusing on the practicality and efficacy of current XAI practices, most works are coming up with new methods of explanations.”
BackgroundExplanation Methods in Deep Learning: Users, Values, Concerns and Challenges
Ras, G., van Gerven, M., & Haselager, P. (2018) · The Springer Series on Challenges in Machine Learning · doi:10.1007/978-3-319-98131-4_2 · Cited by 255
Prototype selection for interpretable classification
Bien, J., & Tibshirani, R. (2011) · The Annals of Applied Statistics · doi:10.1214/11-aoas495 · Cited by 245 · cited 1×
“From a research point of view, some of the widely accepted example-based interpretability techniques are the following: Prototypes and Criticisms Prototypes are a group of chosen examples that accurately depict all the data [140–142].”
MethodA Survey on Big Data Analytics: Challenges, Open Research Issues and Tools
P., D., & Ahmed, K. (2016) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2016.070267 · Cited by 244 · cited 1×
“Also, a major issue rising these days is that there is a lack of awareness about big data [159].”
BackgroundZhao, K., Jia, Z., Jia, F., & Shao, H. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.105860 · Cited by 234 · cited 1×
“Parallel to this developments, financial giants firmly believe that interpretability and explainability are essential prereq-uisites for the use of AI models in thin, highly regulated, opaque, and uncontrollable sectors [64].”
BackgroundLearning Deep Features for Discriminative LocalizationPreprint
Zhou, B., Khosla, A., Lapedriza, À., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.04150 · Cited by 202
Role of machine learning and deep learning in securing 5G-driven industrial IoT applications
Sharma, P., Jain, S., Gupta, S. R., & Chamola, V. (2021) · Ad Hoc Networks · doi:10.1016/j.adhoc.2021.102685 · Cited by 183 · cited 1×
“One of the significant milestones was witnessed in 2016 when an AI player AlphaGo [9, 10], was able to defeat the human world champion Sedol Lee in a game of Go.”
BackgroundSelf-citationAI4VIS: Survey on Artificial Intelligence Approaches for Data Visualization
Wu, A., Wang, Y., Shu, X., Moritz, D., Cui, W., Zhang, H., Zhang, D., & Qu, H. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2021.3099002 · Cited by 182
Emotion classification for short texts: an improved multi-label method
Liu, X., Shi, T., Zhou, G., Liu, M., Yin, Z., Yin, L., & Zheng, W. (2023) · Humanities and Social Sciences Communications · doi:10.1057/s41599-023-01816-6 · Cited by 175 · cited 1×
“Notably, the quality and accuracy of the explanations produced by GPT may depend on the quality and accuracy of the training data, as well as the complexity and character of the black-box model being explained [188, 189].”
BackgroundA Unified Gradient Regularization Family for Adversarial Examples
Lyu, C., Huang, K., & Liang, H.-N. (2015) · 2015 IEEE International Conference on Data Mining · doi:10.1109/icdm.2015.84 · Cited by 169
Self-citationA Study of Today's A.I. through Chatbots and Rediscovery of Machine Intelligence
Khanna, A., Pandey, B., Vashishta, K., Kalia, K., Pradeepkumar, B., & Das, T. (2015) · International Journal of u- and e-Service, Science and Technology · doi:10.14257/ijunesst.2015.8.7.28 · Cited by 162 · cited 1×
“It interprets data and breaks down each sentence into individual words, and each word is used as data for ANN [156] (Fig.”
MethodAgriSegNet: Deep Aerial Semantic Segmentation Framework for IoT-Assisted Precision Agriculture
Anand, T., Sinha, S., Mandal, M., Chamola, V., & Yu, F. R. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3071290 · Cited by 160 · cited 1×
“Existing surveys [21–24] focus on answering “What, Why, and How” to encompass all aspects of XAI.”
BackgroundSelf-citationA Distributionally Robust Optimization Based Method for Stochastic Model Predictive Control
Li, B., Tan, Y., Wu, A.-G., & Duan, G.-R. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2021.3124750 · Cited by 156 · cited 1×
“Although these models are highly optimised on the training data set using [61, 62], user acceptability remains under question.”
BackgroundModeling Relation Paths for Knowledge Graph Completion
Shen, Y., Ding, N., Zheng, H.-T., Li, Y., & Yang, M. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2970044 · Cited by 153 · cited 1×
“Following that, we come to the idea of responsible artificial intelligence, which is an AI that takes into account societal values as well as moral and ethical issues to improve the usability of AI models in real-world applications [27, 28].”
BackgroundLu, Z., Cheng, R., Jin, Y., Tan, K. C., & Deb, K. (2023) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2022.3233364 · Cited by 147 · cited 1×
“Using advanced data processing software, developers can integrate multiple coordinated views to seamlessly explore large-scale deep learning models and predict results, as well as discover patterns [127, 153, 154].”
BackgroundQu, Z., Liu, X., & Zheng, M. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3203791 · Cited by 140 · cited 1×
“Although these models are highly optimised on the training data set using [61, 62], user acceptability remains under question.”
BackgroundQian, Z., Huang, K., Wang, Q., & Zhang, X.-Y. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108889 · Cited by 138
Self-citationDemir-Kavuk, O., Kamada, M., Akutsu, T., & Knapp, E.-W. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-412 · Cited by 133 · cited 1×
“L1 and L2 regularisation provide a novel solution in handling the overfitting and feature selection for such cases [120, 121].”
BackgroundFuzzy Logic and Fuzzy Hybrid Techniques for Construction Engineering and Management
Fayek, A. R. (2020) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0001854 · Cited by 133 · cited 1×
“An explanation of studies using FRBS can be found in [124].”
MethodXAIR: A Systematic Metareview of Explainable AI (XAI) Aligned to the Software Development Process
Clement, T., Kemmerzell, N., Abdelaal, M., & Amberg, M. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5010006 · Cited by 131 · cited 1×
“While partial dependence plots result in a significantly biased computed feature effect, ALEs provide a faster and unbiased substitute for visualisation [138, 139].”
BackgroundEfficient Data Representation by Selecting Prototypes with Importance Weights
Gurumoorthy, K. S., Dhurandhar, A., Cecchi, G., & Aggarwal, C. (2019) · 2019 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2019.00036 · Cited by 131
Uniting cyber security and machine learning: Advantages, challenges and future research
Wazid, M., Das, A. K., Chamola, V., & Park, Y. (2022) · ICT Express · doi:10.1016/j.icte.2022.04.007 · Cited by 130 · cited 1×
“With XAI now being recognised as a necessity rather than just a choice, explanation methods have come a long way, from textual formats to visual aids [29, 30].”
BackgroundSelf-citationCheng, L., Yin, F., Theodoridis, S., Chatzis, S., & Chang, T. (2022) · IEEE Signal Processing Magazine · doi:10.1109/msp.2022.3198201 · Cited by 130 · cited 2×
“Letham et al. [126] proposed a model called Bayesian Rule Lists (BRL), which is based on decision trees as mentioned in [127].”
BackgroundMethodChen, P., Liu, H., Xin, R., Carval, T., Zhao, J., Xia, Y., & Zhao, Z. (2022) · The Computer Journal · doi:10.1093/comjnl/bxac085 · Cited by 128 · cited 1×
“A significant body of work on automated diagnosis and prognosis using machine learning has lately acquired popularity in the medical sector [58, 59].”
BackgroundArtificial Intelligence (AI)-Empowered Intrusion Detection Architecture for the Internet of Vehicles
Alladi, T., Kohli, V., Chamola, V., Yu, F. R., & Guizani, M. (2021) · IEEE Wireless Communications · doi:10.1109/mwc.001.2000428 · Cited by 127 · cited 1×
“[20].”
Self-citationDual-Level Representation Enhancement on Characteristic and Context for Image-Text Retrieval
Yang, S. S., Li, Q., Li, W., Li, X., & Liu, A.-A. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3182426 · Cited by 127 · cited 1×
“Using advanced data processing software, developers can integrate multiple coordinated views to seamlessly explore large-scale deep learning models and predict results, as well as discover patterns [127, 153, 154].”
BackgroundDistill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation
Tan, S., Caruana, R., Hooker, G., & Lou, Y. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278725 · Cited by 125 · cited 1×
“Tan et al. [103]. expanded on the notion of distilling intricate black-box models into transparent ones known as iGAMs through model distillation.”
BackgroundAI-enabled remote monitoring of vital signs for COVID-19: methods, prospects and challenges
Rohmetra, H., Raghunath, N., Narang, P., Chamola, V., Guizani, M., & Lakkaniga, N. R. (2021) · Computing · doi:10.1007/s00607-021-00937-7 · Cited by 120 · cited 1×
“The topic of how to explain ML predictions has generated a lot of discussions [19].”
BackgroundSelf-citationThe Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification
Kim, B., Rudin, C. D., & Shah, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.01161 · Cited by 117
Qian, Z., Huang, K.-Z., Wang, Q.-F., & Zhang, X.-Y. (2022) · Pattern Recognition · doi:10.48550/arxiv.2203.14046 · Cited by 116
Self-citationIteratively Questioning and Answering for Interpretable Legal Judgment Prediction
Zhong, H., Wang, Y., Tu, C., Zhang, T., Liu, Z., & Sun, M. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i01.5479 · Cited by 113 · cited 1×
“With the aim of providing an explanation for legal judgment predictions generated by Legal Judgement Prediction (LJP), Zhong et al. [71] designed the QAjudge.”
How can I choose an explainer?: An Application-grounded Evaluation of Post-hoc Explanations
Jesus, S., Belém, C., Balayan, V., Bento, J., Saleiro, P., Bizarro, P., & Gama, J. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445941 · Cited by 112 · cited 1×
“For example, to diagnose a disease, the most suitable way is for a doctor to perform diagnosis [160].”
BackgroundDCNN-GA: A Deep Neural Net Architecture for Navigation of UAV in Indoor Environment
Chhikara, P., Tekchandani, R., Kumar, N., Chamola, V., & Guizani, M. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3027095 · Cited by 110 · cited 1×
“Unlike the existing literature and studies around XAI, we reflect upon a multidisciplinary approach towards research and development in this emerging field that opens up a new path towards exploring the importance of human–computer interaction (HCI) skills for making transparent models [25, 26].”
BackgroundSelf-citationMachine-Learning-Assisted Security and Privacy Provisioning for Edge Computing: A Survey
Singh, S., Sulthana, R., Shewale, T., Chamola, V., Benslimane, A., & Sikdar, B. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3098051 · Cited by 108 · cited 1×
“Even in a trustworthy field, like movie reviews, it is difficult to interpret whether a review is positive or negative because the movie rating and the emotion do not match [32, 33].”
BackgroundSelf-citationAre explanations always important?: a study of deployed, low-cost intelligent interactive systems
Bunt, A., Lount, M., & Lauzon, C. (2012) · Proceedings of the 2012 ACM international conference on Intelligent User Interfaces · doi:10.1145/2166966.2166996 · Cited by 106 · cited 1×
“In the spirit of holism, Bunt et al. [92] originally raised this question in their work mainly due to the efficiency of explanation techniques deployed in systems that offer users low-cost decisions.”
BackgroundHuynh-Cam, T.-T., Chen, L., & Le, H. (2021) · Algorithms · doi:10.3390/a14110318 · Cited by 106 · cited 1×
“Decision trees function by continuously segmenting the input data into nodes of a tree, each of which represents a subset that belongs to a particular instance from the dataset [122].”
BackgroundOsaba, E., Ser, J. D., Martinez, A. D., & Hussain, A. (2022) · Cognitive Computation · doi:10.1007/s12559-022-10012-8 · Cited by 105 · cited 1×
“Artificial Intelligence (AI) technology is finding its way into transforming various application domains [1, 2].”
BackgroundSelf-citationPupilRec: Leveraging Pupil Morphology for Recommending on Smartphones
Shen, X., Jiang, H., Liu, D., Yang, K., Deng, F., Lui, J. C. S., Liu, J., Dustdar, S., & Luo, J. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3181607 · Cited by 105 · cited 1×
“Overall, the interaction of explainability with AI highlights the importance of developing AI systems that are transparent, interpretable, and trustworthy in order to ensure their responsible and effective deployment in various domains [50–52].”
BackgroundDistilling Knowledge from Deep Networks with Applications to Healthcare Domain
Che, Z., Purushotham, S., Khemani, R. G., & Liu, Y. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.03542 · Cited by 105
Silva, A., Schrum, M., Hedlund-Botti, E., Gopalan, N., & Gombolay, M. (2023) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2022.2101698 · Cited by 104 · cited 1×
“Explainability is becoming increasingly important as AI systems are being used to make decisions that have significant impacts on people’s lives, such as in healthcare, finance, and criminal justice [49].”
BackgroundAPMSA: Adversarial Perturbation Against Model Stealing Attacks
Zhang, J., Peng, S., Gao, Y., Zhang, Z., & Hong, Q. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3246766 · Cited by 102 · cited 1×
“At all times, there is a high risk of data piracy and leak, and businesses are at potential risk of cyber-attacks [158].”
BackgroundEnhance explainability of manifold learning
Han, H., Li, W., Wang, J., Qin, G., & Qin, X. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.05.119 · Cited by 101
TBSM: A traffic burst-sensitive model for short-term prediction under special events
Ren, Y., Jiang, H., Ji, N., & Yu, H. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108120 · Cited by 98 · cited 1×
“Automated transportation has gone from being a topic of science fiction to being a reality thanks to the development of AI [53, 54].”
BackgroundCommon Metrics to Benchmark Human-Machine Teams (HMT): A Review
Damacharla, P., Javaid, A. Y., Gallimore, J. J., & Devabhaktuni, V. K. (2018) · IEEE Access · doi:10.1109/access.2018.2853560 · Cited by 97
Artificial intelligence-assisted blockchain-based framework for smart and secure EMR management
Chamola, V., Goyal, A., Sharma, P., Hassija, V., Bình, H. T. T., & Saxena, V. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07087-7 · Cited by 97 · cited 1×
“Unlike the existing literature and studies around XAI, we reflect upon a multidisciplinary approach towards research and development in this emerging field that opens up a new path towards exploring the importance of human–computer interaction (HCI) skills for making transparent models [25, 26].”
BackgroundSelf-citationCommon Metrics to Benchmark Human-Machine Teams (HMT): A Review
Damacharla, P., Javaid, A. Y., Gallimore, J. J., & Devabhaktuni, V. K. (2020) · arXiv · doi:10.48550/arxiv.2008.04855 · Cited by 97
Long Dialogue Emotion Detection Based on Commonsense Knowledge Graph Guidance
Nie, W., Bao, Y., Zhao, Y., & Liu, A. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3267295 · Cited by 96 · cited 1×
“Exploring new concepts increases the meta information of a person and helps to evaluate individual class predictions by local algorithms [187].”
BackgroundTransparency in a Human-Machine Context: Approaches for Fostering Shared Awareness/Intent
Lyons, J. B., & Havig, P. R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-07458-0_18 · Cited by 96 · cited 1×
“This will allow shared awareness and intent for optimal teamwork [174].”
BackgroundChallenges of human—machine collaboration in risky decision-making
Xiong, W., Fan, H., Ma, L., & Wang, C. (2022) · Frontiers of Engineering Management · doi:10.1007/s42524-021-0182-0 · Cited by 95 · cited 1×
“This refers to some risky decisions that are made using AI [177] (Fig.”
BackgroundExplainable Artificial Intelligence Approaches: A Survey
Islam, S. R., Eberle, W., Ghafoor, S., & Ahmed, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.09429 · Cited by 88
Cresswell, K., Callaghan, M., Khan, S., Sheikh, Z., Mozaffar, H., & Sheikh, A. (2020) · Health Informatics Journal · doi:10.1177/1460458219900452 · Cited by 87 · cited 1×
“These algorithms can take into account a wide range of patient-specific data, including demographic information, laboratory test results, and medication use, to make predictions about a patient’s risk of delirium [60].”
BackgroundSecurity issues in implantable medical devices: Fact or fiction?
Hassija, V., Chamola, V., Bajpai, B. C., Naren, & Zeadally, S. (2021) · Sustainable Cities and Society · doi:10.1016/j.scs.2020.102552 · Cited by 84 · cited 1×
“Entrusting crucial decisions to a black-box model creates a necessary need for AI algorithms to be explainable for their decision-making process [18].”
BackgroundSelf-citationFast Visual Tracking With Siamese Oriented Region Proposal Network
Zhu, H. B., Xue, M., Wang, Y., Yuan, G., & Li, X. (2022) · IEEE Signal Processing Letters · doi:10.1109/lsp.2022.3178656 · Cited by 81 · cited 1×
“Doctors are now able to use medical image technology to diagnose diseases and understand the patient’s condition [79, 80].”
BackgroundExplanations and Expectations: Trust Building in Automated Vehicles
Haspiel, J., Du, N., Meyerson, J., Robert Jr., L. P., Tilbury, D., Yang, X. J., & Pradhan, A. K. (2018) · Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction · doi:10.1145/3173386.3177057 · Cited by 79 · cited 1×
“Contrary to popular belief, Haspiel et al. [57] presented another point of view by investigating the influence of explanations on the trust-building process that were provided at different time frames.”
ResultXAI Handbook: Towards a Unified Framework for Explainable AI
Palacio, S., Lucieri, A., Munir, M., Ahmed, S., Hees, J., & Dengel, A. R. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00420 · Cited by 79 · cited 1×
“Especially from the viewpoint of dynamic environments, constantly flourishing users with modified explanations will ultimately advance the state of the art of explainability [93].”
BackgroundRobust Intelligence and Trust in Autonomous Systems
(2016) · doi:10.1007/978-1-4899-7668-0 · Cited by 78 · cited 2×
“According to the National Highway Traffic Safety Administration, the vehicle was unable to discern between the white side of the truck and a brightly lit sky, preventing the need to brake that may have caused the passengers to suffer significant injuries [55].”
BackgroundA Scenario-Generic Neural Machine Translation Data Augmentation Method
Liu, X., He, J., Liu, M., Yin, Z., Yin, L., & Zheng, W. (2023) · Electronics · doi:10.3390/electronics12102320 · Cited by 78 · cited 1×
“Notably, the quality and accuracy of the explanations produced by GPT may depend on the quality and accuracy of the training data, as well as the complexity and character of the black-box model being explained [188, 189].”
BackgroundGabbay, F., Bar‐Lev, S., Montano, O., & Hadad, N. (2021) · Applied Sciences · doi:10.3390/app112110417 · Cited by 78 · cited 1×
“…can be applied to open a new course of action and hidden laws in various fields like neuro-science, astronomy, etc. Medical research has also confirmed the predictions and early conclusions that were presented by the LIME model and various DNNs, which were not possible by humans at that time [78].”
ResultXie, X., Huang, L., Marson, S. M., & Wei, G. (2023) · Natural Hazards · doi:10.1007/s11069-023-05988-x · Cited by 76 · cited 1×
“A significant body of work on automated diagnosis and prognosis using machine learning has lately acquired popularity in the medical sector [58, 59].”
BackgroundAudioMNIST: Exploring Explainable Artificial Intelligence for audio analysis on a simple benchmark
Becker, S., Vielhaben, J., Ackermann, M., Müller, K.-R., Lapuschkin, S., & Samek, W. (2024) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2023.11.038 · Cited by 73
Bansal, G., Chamola, V., Narang, P., Kumar, S., & Raman, S. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2019.1164 · Cited by 65 · cited 1×
“Taking into consideration the revolutionary success of AI, researchers predict that it will snow-ball in the next few years, reaching $190.61 billion market value in 2025 [13–15].”
BackgroundInfluentialSelf-citationConcurrent Low-power Listening: A New Design Paradigm for Duty-cycling Communication
Liu, D., Cao, Z., Jiang, H., Zhou, S., Xiao, Z. Q., & Zeng, F. (2022) · ACM Transactions on Sensor Networks · doi:10.1145/3517013 · Cited by 65
Practical and Robust Federated Learning With Highly Scalable Regression Training
Han, S., Ding, H., Zhao, S., Ren, S., Wang, Z., Lin, J., & Zhou, S. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3271859 · Cited by 60 · cited 1×
“So , along with a strong foundation, necessary amendments will always help in adding more to the structure of XAI, which will lead to a greater impact [94, 95].”
BackgroundRen, Y., Jiang, H., Feng, X., Zhao, Y., Liu, R., & Yu, H. (2022) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3221927 · Cited by 60 · cited 1×
“Automated transportation has gone from being a topic of science fiction to being a reality thanks to the development of AI [53, 54].”
BackgroundAnbar, M., Abdullah, R., Al-Tamimi, B. N., et al. (2017) · Cognitive Computation · doi:10.1007/s12559-017-9519-8 · Cited by 51
Self-citationThe Technology Acceptance Model: A Meta-Analysis of Empirical Findings
Ma, Q., & Liu, L. (2005) · Advances in End User Computing · doi:10.4018/978-1-59140-474-3.ch006 · Cited by 50
18th International Conference on Artificial Neural Networks
Boukharouba, K., & Lecoeuche, S. (2008) · Cited by 49
Rule Extraction from Training Data Using Neural Network
Biswas, S. K., Chakraborty, M., Purkayastha, B., Roy, P., & Thounaojam, D. M. (2017) · International Journal on Artificial Intelligence Tools · doi:10.1142/s0218213017500063 · Cited by 42 · cited 1×
“To address catego-risation issues, Biswak et al. [101] developed Rule Extraction by Reverse Engineering the Neural Networks (RxREN).”
A blockchain and deep neural networks-based secure framework for enhanced crop protection
Hassija, V., Batra, S., Chamola, V., Anand, T., Goyal, P., Goyal, N., & Guizani, M. (2021) · Ad Hoc Networks · doi:10.1016/j.adhoc.2021.102537 · Cited by 40 · cited 1×
“With XAI now being recognised as a necessity rather than just a choice, explanation methods have come a long way, from textual formats to visual aids [29, 30].”
BackgroundSelf-citationImproving Deep Learning Interpretability by Saliency Guided Training
Ismail, A. A., Bravo, H. C., & Feizi, S. (2021) · arXiv · doi:10.48550/arxiv.2111.14338 · Cited by 38 · cited 1×
“To improve the accuracy of saliency maps, Ismail et al. [165] In machine learning pipelines, the black box is not an option anymore, and there is a tradeoff between performance and interpretability.”
MethodEvaluating the visualization of what a Deep Neural Network has learnedPreprint
Samek, W., Binder, A., Montavon, G., Bach, S., & Müller, K. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.06321 · Cited by 35
ISDNet: AI-enabled Instance Segmentation of Aerial Scenes for Smart Cities
Garg, P., Chakravarthy, A. S., Mandal, M., Narang, P., Chamola, V., & Guizani, M. (2021) · ACM Transactions on Internet Technology · doi:10.1145/3418205 · Cited by 32 · cited 1×
“These models make predictions based on input data, but the decision-making process and reasoning behind the predictions are not transparent to the user [31].”
BackgroundSelf-citationArtificial intelligence as structural estimation: Deep Blue, Bonanza, and AlphaGo
Igami, M. (2020) · The Econometrics Journal · doi:10.1093/ectj/utaa005 · Cited by 28 · cited 1×
“The work of Igami [184] about the connections between machine learning and econometrics laid the foundation for “Structural Econometrics for XAI.””
BackgroundLEAFAGE: Example-based and Feature importance-based Explanations for Black-box ML models
Adhikari, A., Tax, D. M. J., Satta, R., & Faeth, M. (2019) · 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee.2019.8858846 · Cited by 27 · cited 1×
“For some datasets and problems, this approach may provide more accurate and trustworthy explanations than other methods [110, 111].”
The Role of Randomness and Noise in Strategic Classification
Braverman, M., & Garg, S. (2020) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.forc.2020.9 · Cited by 27
EFFECTS OF AUGMENTED SITUATIONAL AWARENESS ON DRIVER TRUST IN SEMI-AUTONOMOUS VEHICLE OPERATION
Petersen, L., Tilbury, D., Robert, L., & Yang, X. J. (2017) · SAE Technical Paper Series · doi:10.4271/2024-01-3654 · Cited by 18 · cited 1×
“Petersen et al. [56] specifically focused on trying to increase passengers’ trust through augmentation of their situational awareness and consideration of actual applications of semi-autonomous vehicles.”
BackgroundA Bibliometric Study and Science Mapping Research of Intelligent Decision
Li, B., Xu, Z., Hong, N., & Hussain, A. (2022) · Cognitive Computation · doi:10.1007/s12559-022-09993-3 · Cited by 18 · cited 1×
“It is essential to note that the highly efficient predictions of AI models are derived from Deep Neural Networks (DNNs) which originate from extremely complex non-linear statistical models and innumerable parameters, thus compromising the aforementioned algorithms’ transparency [16, 17].”
BackgroundSelf-citationEffect of Human-Robot Interaction on the Fleet Size of AIV Transporters in FMS
Martin, L., Gonzalez-Romo, M., Sahnoun, M., Bettayeb, B., He, N., & Gao, J. X. (2021) · International Conference on Cyber Management and Engineering (CyMaEn) · doi:10.1109/cymaen50288.2021.9497273 · Cited by 16 · cited 1×
“The robotics section uses 22% AI automation, while the company’s patented cognitive technology uses around 43% [170, 171].”
MethodInterpreting Deep Classifier by Visual Distillation of Dark Knowledge
Xu, K., Park, D. H., Yi, C., & Sutton, C. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.04042 · Cited by 16
Artificial Intelligence and Machine Learning for the Industrial Internet of Things (IIoT)
Raheem, F., & Iqbal, N. (2022) · doi:10.1201/9781003145004-1 · Cited by 14 · cited 1×
“For now, new talent who are proficient at developing AI models which are explainable needs to be recruited [175].”
BackgroundKadir, M. A., Mosavi, A. H., & Sonntag, D. (2023) · Engineering Archive (engrXiv) · doi:10.31224/2989 · Cited by 13
Holzinger, A., Carrington, A., & Müller, H. (2019) · arXiv · doi:10.48550/arxiv.1912.09024 · Cited by 11
Price of Transparency in Strategic Machine Learning
Akyol, E., Langbort, C., & Basar, T. (2016) · arXiv · doi:10.48550/arxiv.1610.08210 · Cited by 11
Explaining and predicting abnormal expenses at large scale using knowledge graph based reasoning
Lecue, F., & Wu, J. (2017) · Journal of Web Semantics · doi:10.1016/j.websem.2017.05.003 · Cited by 9 · cited 1×
“Lecue and Wu [65] successfully predicted abnormal expenses through combined knowledge of Semantic Web and ML technologies.”
BackgroundMitigating the Rashomon Effect in Counterfactual Explanation: A Game-theoretic Approach
Hasan, M. G. M. M., & Talbert, D. A. (2022) · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference · doi:10.32473/flairs.v35i.130711 · Cited by 8 · cited 1×
“Hasan et al. [146] realised the need to mitigate this effect and proposed a game-theory perspective to make counterfactuals more intriguing.”
BackgroundQian, M., & Qian, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-50334-5_5 · Cited by 8 · cited 1×
“In the continuous circle of learning between humans and machines, there is a mutual transfer of knowledge [176].”
BackgroundInterpretable Movie Review Analysis Using Machine Learning and Transformer Models Leveraging XAI
Ahmed, F., Sultana, S., Reza, M. T., Joy, S. K. S., & Alam, M. G. R. (2022) · IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) · doi:10.1109/csde56538.2022.10089294 · Cited by 7 · cited 1×
“Even in a trustworthy field, like movie reviews, it is difficult to interpret whether a review is positive or negative because the movie rating and the emotion do not match [32, 33].”
BackgroundDiscriminative Dictionary Design for Action Classification in Still Images and Videos
Roy, A., Banerjee, B., Hussain, A., & Poria, S. (2021) · Cognitive Computation · doi:10.1007/s12559-021-09851-8 · Cited by 7
Self-citationAudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark
Becker, S., Vielhaben, J., Ackermann, M., Müller, K.-R., Lapuschkin, S., & Samek, W. (2018) · arXiv · doi:10.48550/arxiv.1807.03418 · Cited by 7
Extracting symbolic rules from trained neural network ensembles
ZhouZhi-Hua, JiangYuan, & ChenShi-Fu (2003) · AI Communications · doi:10.5555/859130.859132 · Cited by 5
Ahmed, M. E. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/7325064 · Cited by 4
Mittu, R., Sofge, D., Wagner, A. R., & Lawless, W. F. (2016) · Springer eBooks · doi:10.1007/978-1-4899-7668-0_1 · Cited by 3
Perelman, B. S., Mueller, S. T., & Schaefer, K. E. (2017) · doi:10.1109/cogsima.2017.7929595 · Cited by 2 · cited 1×
“The robotics section uses 22% AI automation, while the company’s patented cognitive technology uses around 43% [170, 171].”
MethodExplanation Methods in Deep Learning: Users, Values, Concerns and Challenges
Ras, G., van Gerven, M., & Haselager, P. (2018) · arXiv · doi:10.48550/arxiv.1803.07517
Efficient Data Representation by Selecting Prototypes with Importance Weights
Gurumoorthy, K. S., Dhurandhar, A., Cecchi, G., et al. (2017) · arXiv · doi:10.48550/arxiv.1707.01212
Building Neural Network Ensembles using Genetic Programming
Johansson, U., Lofstrom, T., Konig, R., & Niklasson, L. (n.d.) · The 2006 IEEE International Joint Conference on Neural Network Proceedings · doi:10.1109/ijcnn.2006.1716247
Research works printed but not linked: 11
- 3. Li XH, Cao CC, Shi Y, Bai W, Gao H, Qiu L, Wang C, Gao Y, Zhang S, Xue X, Chen L. A survey of data-driven and knowledge-aware explainable ai. IEEE Trans Knowl Data Eng. 2022;34(1):29-49.
- 8. Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. arXiv. 2014.
- 45. Becker S, Ackermann M, Lapuschkin S, Müller K, Samek W. Interpreting and explaining deep neural networks for classification of audio signals. CoRR. 2018;abs/1807.03418. http:// arxiv. org/ abs/ 1807. 03418.
- 98. Johansson U, König R, Niklasson L. Rule extraction from trained neural networks using genetic programming. In: 13th Interna- tional Conference on Artificial Neural Networks. 2003. p. 13-6.
- Sarkar S, Weyde T, d’Avila Garcez AS, Slabaugh GG, Dragicevic S, Percy C. Accuracy and interpretability trade-offs in machine learning applied to safer gambling. In: CoCo@NIPS. 2016.
- 104. Green D, Kern H. Modeling heterogeneous treatment effects in large-scale experiments using Bayesian additive regression trees. Iowa City: The Annual Summer Meeting of the Society of Political Methodology; 2010. 132. Elith J, Leathwick JR, Hastie T. A working guide to boosted regression trees. J Anim Ecol. 2008;77(4):802-13. https:// besjo urnals. onlin elibr ary. wiley. com. 133. Goldstein A, Kapelner A, Bleich J, Pitkin E. Peeking inside the black box: Visualizing statistical learning with plots of indi- vidual conditional expectation. J Comput Graph Stat. 2013;24. 134.
- 111. Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Fergus R. Intriguing properties of neural networks. 2013. https:// arxiv. org/ abs/ 1312. 6199. 148. Su J, Vargas D, Sakurai K. One pixel attack for fooling deep neural networks. IEEE Trans Evolut Comput. 2017. 149.
- Sadiku M, Shadare A, Musa S, Akujuobi C, Perry R. Data visualization. Int J Eng Res Adv Technol (IJERAT). 2016;12:2454–6135.
- Chang J, Boyd-Graber J, Gerrish S, Wang C, Blei D. Reading tea leaves: how humans interpret topic models. vol 32. 2009. p. 288–96.
- Ballav A, Ghosh M. Human factors of human machine interaction: Analyzing future trends through the past and the present. Int J Res. 2017;4:138–44.
- Xiong W, Fan H, Ma L, Wang C. Challenges of human—machine collaboration in risky decision-making. Front Eng Manag. 2022;9(1):89–103. · DOI · Paper page
Cited by
Vimbi, V., Shaffi, N., & Mahmud, M. (2024) · Brain Informatics · doi:10.1186/s40708-024-00222-1 · Cited by 433
“While ML and DL models have shown great promise in AD prediction, their black-box nature remains a significant hurdle to their adoption in real-world scenarios [81].”
BackgroundMethodSelf-citationMarques, L., Costa, B., Pereira, M., Silva, A., Santos, J., Saldanha, L., Silva, I., Magalhães, P., Schmidt, S., & Vale, N. (2024) · Pharmaceutics · doi:10.3390/pharmaceutics16030332 · Cited by 390
“Advanced models can play a pivotal role in verifying the accurate application of de-identification techniques, thereby promoting both data confidentiality and usability while aligning with ethical and regulatory standards [214].”
BackgroundExplainable artificial intelligence (XAI) in finance: a systematic literature review
Černevičienė, J., & Kabašinskas, A. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10854-8 · Cited by 289
Ethical and legal considerations in healthcare AI: innovation and policy for safe and fair use
Pham, T. (2025) · Royal Society Open Science · doi:10.1098/rsos.241873 · Cited by 261
Babatunde, S. O., Odejide, O. A., Edunjobi, T. E., & Ogundipe, D. O. (2024) · International Journal of Management & Entrepreneurship Research · doi:10.51594/ijmer.v6i3.964 · Cited by 247
Metadata
- Authors
- Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., & Hussain, A.
- Affiliations
- KIIT University (IN)
- Birla Institute of Technology and Science, Pilani (IN)
- Jaypee Institute of Information Technology (IN)
- Duke Kunshan University (CN)
- Sapienza University of Rome (IT)
- Istituto Nazionale di Fisica Nucleare, Sezione di Roma I (IT)
- Nottingham Trent University (GB)
- Edinburgh Napier University (GB)
- Corresponding author
- Hassija, Vikas
- Chamola, Vinay
- Singal, Abhinandan
- Goel, Divyansh
- Huang, Kaizhu
- Scardapane, Simone
- Spinelli, Indro
- Mahmud, Mufti
- Hussain, Amir
- ORCID
- Venue
- Cognitive Computation
- Published
- 2023-08-24
- Volume
- 16
- Issue
- 1
- Pages
- 45-74
- ISSN
- 1866-9956 (ISSN-L)
- 1866-9964
- OpenAlex
- W4386142022
- Semantic Scholar
- 20c02c51420a69ae39b74d8d73148417819dacc1
- Cited by
- 2,495
- References
- 139
- Citations by year
- 2026: 1109 · 2025: 1030 · 2024: 338 · 2023: 18
- FWCI
- 177.44
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Cognitive Computation (publishedVersion, cc-by)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion, other-oa)
- Edinburgh Napier Research Repository (Edinburgh Napier University) (submittedVersion, other-oa)
- Funders
- European Commission (618615-EPP-1-2020-1-UKEPPKA2-CBHEJP, 2020-1-UK01-KA201-079167)
- Erasmus+ (618615-EPP-1-2020-1-UK-EPPKA2-CBHE-JP, 2020-1-UK01-KA201-079167)
- CHIST-ERA (CHIST-ERA-19-XAI-009)
- 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, black-box models, model interpretability, model transparency, decision explanation, machine learning model evaluation, deep learning model interpretability
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
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.