The DOI matches its Crossref record; 204 of the 208 references it cites were found in a registry or an index, and 4 are not checked yet; 17 of the 124 sources its claims cite were checked for support.
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
Open accessAbstract
The rising popularity of explainable artificial intelligence (XAI) to understand high-performing black boxes raised the question of how to evaluate explanations of machine learning (ML) models. While interpretability and explainability are often presented as a subjectively validated binary property, we consider it a multi-faceted concept. We identify 12 conceptual properties, such as Compactness and Correctness, that should be evaluated for comprehensively assessing the quality of an explanation. Our so-called Co-12 properties serve as categorization scheme for systematically reviewing the evaluation practices of more than 300 papers published in the past 7 years at major AI and ML conferences that introduce an XAI method. We find that one in three papers evaluate exclusively with anecdotal evidence, and one in five papers evaluate with users. This survey also contributes to the call for objective, quantifiable evaluation methods by presenting an extensive overview of quantitative XAI evaluation methods. Our systematic collection of evaluation methods provides researchers and practitioners with concrete tools to thoroughly validate, benchmark, and compare new and existing XAI methods. The Co-12 categorization scheme and our identified evaluation methods open up opportunities to include quantitative metrics as optimization criteria during model training to optimize for accuracy and interpretability simultaneously.
Verified 2026-10-05 · 4 references not checked yet
Overview
CoChat Summary
TL;DR
This systematic review analyzes how explainable AI methods are evaluated, proposing 12 conceptual explanation-quality properties (Co-12) and cataloging quantitative evaluation methods. Across 606 screened papers from 2014–2020 at 12 major conferences, 312 introduced an XAI method, and the authors find that 33% evaluate only with anecdotal evidence, 58% use quantitative evaluation, and 22% use user studies.
Key findings
- Of the 312 papers introducing an XAI method, 33% evaluated exclusively with anecdotal evidence, 58% applied quantitative evaluation, and 22% evaluated with human subjects in a user study; of those user studies, 23% used domain experts (application-grounded).
- The Co-12 properties are proposed as a multi-faceted categorization scheme; the most frequently evaluated properties were Coherence and Output-completeness, followed by Correctness, Compactness, and Covariate complexity.
- Most papers that quantitatively evaluated an XAI method evaluated only one or two Co-12 properties; 73 papers evaluated exactly one property, often Coherence.
- Quantitative evaluation methods exist for each Co-12 property, but evaluation practice remains concentrated on Coherence, Completeness, Compactness, and Correctness; the authors also report that quantitative evaluation slightly increased over time while anecdotal-only evaluation decreased, with user studies remaining around 20%.
Methods
- Systematic literature review: DBLP title keyword search (`explain* OR explanat* OR interpret*`) across 12 conferences (AAAI, IJCAI, NeurIPS, ICML, ICLR, CVPR, ICCV, ACL, WWW, ICDM, SIGKDD, SIGIR) for 2014–2020, conducted 4 May 2021; 606 papers found, 494 after excluding companion papers, 361 included after inclusion criteria, and 312 after filtering to papers introducing an XAI method.
- Each included paper was categorized along six dimensions (data type, explanation type, explanation problem, predictive model type, task type, method type) and reviewed for evaluation practices using the Co-12 properties; user studies were classified as application-grounded or human-grounded following Doshi-Velez and Kim.
- The review focuses on functionally grounded, quantitative evaluation methods without user studies, with user-study evaluation methods summarized in Supplementary Material; quantitative methods were clustered and named according to the Co-12 properties.
Limitations
- The paper states that it focuses on functionally grounded evaluation and provides only a concise overview of user-study evaluation methods in Supplementary Material.
- The paper states that it may be unreasonable to expect an XAI method to score well on all Co-12 properties, and that trade-offs are necessary: Coherence may contradict Correctness, and Completeness and Compactness may be diametrical opposites; application domain and practical feasibility determine which properties should be emphasized.
- The text makes evident that the corpus is limited to 12 computer science conferences from 2014–2020 and uses title keyword search, so coverage may miss other venues, terms, or later work; the authors also note that their venue selection may have influenced the higher quantitative-evaluation statistics, and Figure 5 notes that a manually added category may be high precision but potentially low recall.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
10 Valid · 3 Not valid · 63 Not checked · 97 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Since we could not find a complete and recent overview of explanation types, we reviewed recent XAI surveys [14,58,167,280] and adapted and extended the categories identified by Guidotti et al. [86] with these insights.”
§ From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI > Text
What the sources say
- Not checked yetcites [14]
- Not checked yetcites [58]
- Not checked yetcites [167]
- Not checked yetcites [280]
- Partly supportedcites [86] sourceExperimental — accuracy not yet measured
Guidotti et al. do state a coverage gap: the Introduction (1 Introduction, p. 3) says 'Existing works tend to provide just a general overview of the problem [59] highlighting unanswered questions and problems [24]' while others 'focus on particular aspects', so 'a clear classification considering simultaneously all these aspects is needed' — this supports the 'not a complete overview' part of the claim. What our copy does not support is the 'recent' qualifier: the paper never says the missing overview is a matter of recency (it says prior works are partial in scope, and its own Conclusion, p. 37, presents 'a comprehensive overview of methods proposed in the literature'). Separately, the categories the citing sentence credits to them are genuinely theirs (four problem categories plus the classification dimensions of Section 5, p. 16), so that half of the attribution holds. (LLM, conf=0.70)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Others do not explicitly evaluate their method with quantitative evaluation metrics, but present mathematical theory to support their claims (e.g., [39,98]).”
§ From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI > Our summary statistics on XAI evaluation:
What the sources say
- Partly supportedcites [39] sourceExperimental — accuracy not yet measured
The Introduction (p. 1) explicitly says the authors provide theoretical support for LS-Tree by relating it to the Banzhaf value. But the paper also reports quantitative experiments: Detecting overfitting (pp. 6–7) evaluates an LS-Tree-based diagnostic using interaction-score variances and permutation-test p-values. The claim that this paper does not explicitly evaluate its method quantitatively is therefore not supported without a narrower meaning of ‘evaluation metrics.’ (LLM, conf=0.83)
- Not checked yetcites [98]
plain- 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 support only part of this claim — read each source’s verdict below.
In the paper
“Besides using Incremental Deletion/Addition to evaluate correctness and output-completeness, compactness can be evaluated by counting how many features of the explanation need to be removed, perturbed or added to change the decision of the predictive model [7,34,70,123,165,221].”
§ From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI > Incremental Deletion/Addition can include the evaluation of output-completeness.
What the sources say
- Partly supportedcites [7] sourceExperimental — accuracy not yet measured
In §5 (Experiments; page unavailable), the paper evaluates explanation cardinality and length and separately counts changes to variables needed to change a Bayesian classifier’s classification. It does not evaluate compactness by counting features removed, perturbed, or added to an explanation; the counted changes are changes to variable values. The cited passages also do not discuss Incremental Deletion/Addition. (LLM, conf=0.84)
- Not checked yetcites [34]
- Partly supportedcites [70] sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
- Partly supportedcites [123] sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 1 unverifiable. Expand the claim to see per-atom verdicts.
- Partly supportedcites [165] sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
- Partly supportedcites [221] sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
plain- 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.
- Rests on an assumption not shown here.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“If a model is successfully trained on a dataset with random labels, which has been shown to be possible with deep neural networks [294], then it has learned the data generation process by memorizing the random labels.”
§ From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI > 6.5 Functionally Evaluating Contrastivity
What the sources say
- Supportedcites [294] source
The citation is attached specifically to 'which has been shown to be possible with deep neural networks', and our copy states exactly that in Section 1.1 (The randomization test): 'Deep neural networks easily fit random labels... when trained on a completely random labeling of the true data, neural networks achieve 0 training error', with implication 1 being that 'the effective capacity of neural networks is sufficient for memorizing the entire data set'; Section 2.1 repeats this for CIFAR10 and ImageNet. So the fitted-random-labels-by-memorization part attributed to Zhang et al. is supported. Note that the sentence's consequent ('learned the data generation process') is the citing authors' own inference rather than something credited to this source; the source in fact says the opposite there ('the randomization breaks any relationship between the instance... and the label... By design, no generalization is possible on the randomized data'), so that framing should not be read back onto citation [294]. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Indirectly, these metrics also evaluate composition, since it has been shown that ROUGE and BLEU correlate with human judgments on fluency of a text [67].”
§ From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI > 6.11 Functionally Evaluating Coherence
What the sources say
- Supportedcites [67] source
Table 2 of Section 5.2 (pp. 9-10, rendered at p. 5 of our copy) reports Kendall's tau correlations between automatic metrics and expert human judgments per dimension: ROUGE variants reach 0.48-0.55 on Fluency (ROUGE-1 0.5240, ROUGE-4 0.5535) and BLEU 0.3321, i.e. both are positively correlated with human fluency ratings. The accompanying text confirms the trend: 'Model correlations increase considerably across the consistency and fluency dimensions' (5.2, p. 9). The only qualifier the citing sentence drops is scope: these correlations were computed system-level on CNN/DailyMail summarization outputs with multi-reference metrics, not on text fluency in general. (LLM, conf=0.82)
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.
- Supported
74 more claims
Create a free account to see all 173 claims and to verify the 107 references still open.
- Probably not a substantial claim. 70
- It may state two separate claims as one. 47
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
“However, a process for evaluating AI output has yet to be standardized.”
From Procedure to Evaluate Artificial Intelligence (AI) Output for Educational and Clinical Tasks (2026) · cites this paper as Nauta et al., 2023
Experimental — accuracy not yet measuredIn the citing paper
“How to evaluate these methods and their explanations is still a popular research challenge [111,114,115], and further research is needed in this context.”
From Survey of Explainable AI Techniques in Healthcare (2023) · cites this paper as [114]
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
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×
“Examples include Partial Dependence Plot [72], Individual Conditional Expectation plot [81] and Feature Auditing [5].”
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
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
"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
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 5×
“We consider related concepts such as fairness, safety, causality, ethical decision making and privacy [21, 63, 150] out of scope.”
BackgroundMethodInfluentialRudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 2×
“We hypothesize that the model explanation is not often addressed since there is no guarantee that the original black box and the interpretable surrogate model agree on their internal reasoning [217].”
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 5×
“We consider related concepts such as fairness, safety, causality, ethical decision making and privacy [21, 63, 150] out of scope.”
BackgroundMethodInfluentialPeeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294 · cited 6×
“The necessity for interpretable and explainable AI (XAI) therefore arises, aiming to make AI systems and their results more understandable to humans [1].”
BackgroundMethodResultInfluentialLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Research works printed but not linked: 102
- Tameem Adel, Zoubin Ghahramani, and Adrian Weller. 2018. Discovering interpretable representations for both deep generative and discriminative models. In Proceedings of the ICML, Vol. 80. PMLR.
- David Alvarez-Melis and Tommi S. Jaakkola. 2018. Towards robust interpretability with self-explaining neural networks. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2018/hash/3e9f0fc9b2f89e043bc6233994dfcf76-Abstract.html.
- Marco Ancona, Cengiz Öztireli, and Markus H. Gross. 2019. Explaining deep neural networks with a polynomial time algorithm for shapley value approximation. In Proceedings of the ICML, Vol. 97. PMLR.
- Marco Ancona, Cengiz Öztireli, Enea Ceolini, and Markus Gross. 2017. A unified view of gradient-based attribution methods for Deep Neural Networks. In Proceedings of the NIPS Workshop on Interpreting, Explaining and Visualizing Deep Learning.
- Christopher J. Anders, Plamen Pasliev, Ann-Kathrin Dombrowski, Klaus-Robert Müller, and Pan Kessel. 2020. Fairwashing explanations with off-manifold detergent. In Proceedings of the ICML, Vol. 119. PMLR.
- Vijay Arya Rachel K. E. Bellamy Pin-Yu Chen Amit Dhurandhar Michael Hind Samuel C. Hoffman Stephanie Houde Q Vera Liao Ronny Luss Aleksandra Mojsilović et al. 2019. One explanation does not fit all: A toolkit and taxonomy of ai explainability techniques. Retrieved from https://arXiv:1909.03012.
- Cher Bass, Mariana da Silva, Carole H. Sudre, Petru-Daniel Tudosiu, Stephen M. Smith, and Emma C. Robinson. 2020. ICAM: Interpretable classification via disentangled representations and feature attribution mapping. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/56f9f88906aebf4ad985aaec7fa01313-Abstract.html.
- Or Biran and Courtenay Cotton. 2017. Explanation and justification in machine learning: A survey. In Proceedings of the IJCAI Workshop on XAI.
- Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang, Cynthia Liu, Pin-Yu Chen, Shiyu Chang, and Luca Daniel. 2020. Proper network interpretability helps adversarial robustness in classification. In Proceedings of the ICML, Vol. 119. PMLR.
- Prasad Chalasani, Jiefeng Chen, Amrita Roy Chowdhury, Xi Wu, and Somesh Jha. 2020. Concise explanations of neural networks using adversarial training. In Proceedings of the ICML, Vol. 119. PMLR. http://proceedings.mlr.press/v119/chalasani20a.html.
- Chun-Hao Chang, Elliot Creager, Anna Goldenberg, and David Duvenaud. 2019. Explaining image classifiers by counterfactual generation. In Proceedings of the ICLR. OpenReview.net. Retrieved from https://openreview.net/forum?id=B1MXz20cYQ.
- Chaofan Chen, Oscar Li, Daniel Tao, Alina Barnett, Cynthia Rudin, and Jonathan Su. 2019. This looks like that: Deep learning for interpretable image recognition. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2019/hash/adf7ee2dcf142b0e11888e72b43fcb75-Abstract.html.
- Jianbo Chen, Le Song, Martin J. Wainwright, and Michael I. Jordan. 2018. Learning to explain: An information-theoretic perspective on model interpretation. In Proceedings of the ICML, Vol. 80. PMLR.
- Jianbo Chen, Le Song, Martin J. Wainwright, and Michael I. Jordan. 2019. L-shapley and C-shapley: Efficient model interpretation for structured data. In Proceedings of the ICLR. OpenReview.net. Retrieved from https://openreview.net/forum?id=S1E3Ko09F7.
- Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, and Pieter Abbeel. 2016. InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2016/hash/7c9d0b1f96aebd7b5eca8c3edaa19ebb-Abstract.html.
- Michael Chromik and Martin Schuessler. 2020. A taxonomy for human subject evaluation of black-box explanations in XAI. In Proceedings of the ExSS-ATEC’20.
- Jonathan Crabbé, Yao Zhang, William R. Zame, and Mihaela van der Schaar. 2020. Learning outside the Black-Box: The pursuit of interpretable models. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/ce758408f6ef98d7c7a7b786eca7b3a8-Abstract.html.
- Mark W. Craven and Jude W. Shavlik. 1995. Extracting tree-structured representations of trained networks. In Proceedings of the NIPS. MIT Press. Retrieved from http://papers.nips.cc/paper/1152-extracting-tree-structured-representations-of-trained-networks.
- Arun Das and Paul Rad. 2020. Opportunities and challenges in explainable artificial intelligence (xai): A survey. Retrieved from https://arXiv:2006.11371.
- Amit Dhurandhar, Pin-Yu Chen, Ronny Luss, Chun-Chen Tu, Pai-Shun Ting, Karthikeyan Shanmugam, and Payel Das. 2018. Explanations based on the missing: Towards contrastive explanations with pertinent negatives. In Proceedings of the NeurIPS.
- Ann-Kathrin Dombrowski, Maximilian Alber, Christopher J. Anders, Marcel Ackermann, Klaus-Robert Müller, and Pan Kessel. 2019. Explanations can be manipulated and geometry is to blame. In Proceedings of the NeurIPS.
- Christian Etmann, Sebastian Lunz, Peter Maass, and Carola Schönlieb. 2019. On the connection between adversarial robustness and saliency map interpretability. In Proceedings of the ICML, Vol. 97. PMLR. Retrieved from http://proceedings.mlr.press/v97/etmann19a.html.
- Vincent Fortuin, Matthias Hüser, Francesco Locatello, Heiko Strathmann, and Gunnar Rätsch. 2019. SOM-VAE: Interpretable discrete representation learning on time series. In Proceedings of the ICLR.
- Christopher Frye, Colin Rowat, and Ilya Feige. 2020. Asymmetric shapley values: Incorporating causal knowledge into model-agnostic explainability. In Proceedings of the NeurIPS.
- Amirata Ghorbani, James Wexler, James Y. Zou, and Been Kim. 2019. Towards automatic concept-based explanations. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2019/hash/77d2afcb31f6493e350fca61764efb9a-Abstract.html.
- Yash Goyal, Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Counterfactual visual explanations. In Proceedings of the ICML, Vol. 97. PMLR. Retrieved from http://proceedings.mlr.press/v97/goyal19a.html.
- Tian Guo, Tao Lin, and Nino Antulov-Fantulin. 2019. Exploring interpretable LSTM neural networks over multi-variable data. In Proceedings of the ICML, Vol. 97. PMLR.
- Wenbo Guo, Sui Huang, Yunzhe Tao, Xinyu Xing, and Lin Lin. 2018. Explaining deep learning models - a bayesian non-parametric approach. In Proceedings of the NeurIPS.
- Peter Hase, Harry Xie, and Mohit Bansal. 2021. The out-of-distribution problem in explainability and search methods for feature importance explanations. In Proceedings of the NeurIPS, Vol. 34. Curran Associates, Inc.
- Juyeon Heo, Sunghwan Joo, and Taesup Moon. 2019. Fooling neural network interpretations via adversarial model manipulation. In Proceedings of the NeurIPS.
- Jay Heo, Haebeom Lee, Saehoon Kim, Juho Lee, Kwang Joon Kim, Eunho Yang, and Sung Ju Hwang. 2018. Uncertainty-aware attention for reliable interpretation and prediction. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2018/hash/285e19f20beded7d215102b49d5c09a0-Abstract.html.
- Bernease Herman. 2017. The promise and peril of human evaluation for model interpretability. Retrieved from https://arXiv:1711.07414.
- Tom Heskes, Evi Sijben, Ioan Gabriel Bucur, and Tom Claassen. 2020. Causal shapley values: Exploiting causal knowledge to explain individual predictions of complex models. In Proceedings of the NeurIPS.
- Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs trained by a two time-scale update rule converge to a local nash equilibrium. In Proceedings of the NeurIPS, Vol. 30. Curran Associates, Inc.
- Robert R. Hoffman Shane T. Mueller Gary Klein and Jordan Litman. 2019. Metrics for explainable AI: Challenges and prospects. Retrieved from https://arXiv:1812.04608.
- Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, and Been Kim. 2019. A benchmark for interpretability methods in deep neural networks. In Proceedings of the NeurIPS.
- Lukas Hoyer, Mauricio Munoz, Prateek Katiyar, Anna Khoreva, and Volker Fischer. 2019. Grid saliency for context explanations of semantic segmentation. In Proceedings of the NeurIPS.
- Wei-Ning Hsu, Yu Zhang, and James R. Glass. 2017. Unsupervised learning of disentangled and interpretable representations from sequential data. In Proceedings of the NeurIPS.
- Aya Abdelsalam Ismail, Mohamed K. Gunady, Héctor Corrada Bravo, and Soheil Feizi. 2020. Benchmarking deep learning interpretability in time series predictions. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/47a3893cc405396a5c30d91320572d6d-Abstract.html.
- Wengong Jin, Regina Barzilay, and Tommi S. Jaakkola. 2020. Multi-objective molecule generation using interpretable substructures. In Proceedings of the ICML, Vol. 119. PMLR. Retrieved from http://proceedings.mlr.press/v119/jin20b.html.
- Xisen Jin, Zhongyu Wei, Junyi Du, Xiangyang Xue, and Xiang Ren. 2020. Towards hierarchical importance attribution: Explaining compositional semantics for neural sequence models. In Proceedings of the ICLR. OpenReview.net. Retrieved from https://openreview.net/forum?id=BkxRRkSKwr.
- Been Kim, Oluwasanmi Koyejo, and Rajiv Khanna. 2016. Examples are not enough, learn to criticize! Criticism for interpretability. In Proceedings of the NeurIPS.
- Been Kim, Martin Wattenberg, Justin Gilmer, Carrie J. Cai, James Wexler, Fernanda B. Viégas, and Rory Sayres. 2018. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV). In Proceedings of the ICML, Vol. 80. PMLR.
- Hyunjik Kim and Andriy Mnih. 2018. Disentangling by factorising. In Proceedings of the ICML, Vol. 80. PMLR.
- Wonjae Kim and Yoonho Lee. 2019. Learning dynamics of attention: Human prior for interpretable machine reasoning. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2019/hash/ae3539867aaeec609a4260c6feb725f4-Abstract.html.
- Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber, Klaus-Robert Müller, Dumitru Erhan, Been Kim, and Sven Dähne. 2018. Learning how to explain neural networks: PatternNet and pattern attribution. In Proceedings of the ICLR.
- Isaac Lage Emily Chen Jeffrey He Menaka Narayanan Been Kim Sam Gershman and Finale Doshi-Velez. 2019. An evaluation of the human-interpretability of explanation. Retrieved from https://arXiv:1902.00006.
- Isaac Lage, Andrew Slavin Ross, Samuel J. Gershman, Been Kim, and Finale Doshi-Velez. 2018. Human-in-the-loop interpretability prior. In Proceedings of the NeurIPS.
- Himabindu Lakkaraju, Nino Arsov, and Osbert Bastani. 2020. Robust and stable black box explanations. In Proceedings of the ICML, Vol. 119. PMLR.
- Himabindu Lakkaraju and Jure Leskovec. 2016. Confusions over time: An interpretable bayesian model to characterize trends in decision making. In Proceedings of the NeurIPS.
- Matthew L. Leavitt and Ari Morcos. 2020. Towards falsifiable interpretability research. Retrieved from https://arXiv:2010.12016.
- Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Proceedings of the Text Summarization Branches Out. ACL.
- Yang Liu, Sujay Khandagale, Colin White, and Willie Neiswanger. 2021. Synthetic benchmarks for scientific research in explainable machine learning. In Proceedings of the NeurIPS Datasets and Benchmarks Track.
- Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Proceedings of the NeurIPS.
- Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, and Xiang Zhang. 2020. Parameterized explainer for graph neural network. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/e37b08dd3015330dcbb5d6663667b8b8-Abstract.html.
- José Oramas M., Kaili Wang, and Tinne Tuytelaars. 2019. Visual explanation by interpretation: Improving visual feedback capabilities of deep neural networks. In Proceedings of the ICLR. OpenReview.net. Retrieved from https://openreview.net/forum?id=H1ziPjC5Fm.
- João Marques-Silva, Thomas Gerspacher, Martin C. Cooper, Alexey Ignatiev, and Nina Narodytska. 2020. Explaining naive bayes and other linear classifiers with polynomial time and delay. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/eccd2a86bae4728b38627162ba297828-Abstract.html.
- Tim Miller, Piers Howe, and Liz Sonenberg. 2017. Explainable AI: Beware of inmates running the asylum or: How I learnt to stop worrying and love the social and behavioural sciences. In Proceedings of the IJCAI Workshop on Explainable Artificial Intelligence.
- Jesse Mu and Jacob Andreas. 2020. Compositional explanations of neurons. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/c74956ffb38ba48ed6ce977af6727275-Abstract.html.
- Anh Nguyen, Alexey Dosovitskiy, Jason Yosinski, Thomas Brox, and Jeff Clune. 2016. Synthesizing the preferred inputs for neurons in neural networks via deep generator networks. In Proceedings of the NeurIPS, Vol. 29. Curran Associates, Inc. Retrieved from https://proceedings.neurips.cc/paper/2016/file/5d79099fcdf499f12b79770834c0164a-Paper.pdf.
- Weili Nie, Yang Zhang, and Ankit Patel. 2018. A theoretical explanation for perplexing behaviors of backpropagation-based visualizations. In Proceedings of the ICML, Vol. 80. PMLR. Retrieved from http://proceedings.mlr.press/v80/nie18a.html.
- Matthew R. O’Shaughnessy, Gregory Canal, Marissa Connor, Christopher Rozell, and Mark A. Davenport. 2020. Generative causal explanations of black-box classifiers. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/3a93a609b97ec0ab0ff5539eb79ef33a-Abstract.html.
- Jung Yeon Park, Kenneth Theo Carr, Stephan Zheng, Yisong Yue, and Rose Yu. 2020. Multiresolution tensor learning for efficient and interpretable spatial analysis. In Proceedings of the ICML, Vol. 119. PMLR.
- Tejaswini Pedapati, Avinash Balakrishnan, Karthikeyan Shanmugam, and Amit Dhurandhar. 2020. Learning global transparent models consistent with local contrastive explanations. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/24aef8cb3281a2422a59b51659f1ad2e-Abstract.html.
- Vitali Petsiuk, Abir Das, and Kate Saenko. 2018. RISE: Randomized input sampling for explanation of black-box models. In Proceedings of the BMVC.
- Gregory Plumb, Maruan Al-Shedivat, Ángel Alexander Cabrera, Adam Perer, Eric P. Xing, and Ameet Talwalkar. 2020. Regularizing black-box models for improved interpretability. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/770f8e448d07586afbf77bb59f698587-Abstract.html.
- Gregory Plumb, Denali Molitor, and Ameet S. Talwalkar. 2018. Model agnostic supervised local explanations. In Proceedings of the NeurIPS.
- Gregory Plumb, Jonathan Terhorst, Sriram Sankararaman, and Ameet Talwalkar. 2020. Explaining groups of points in low-dimensional representations. In Proceedings of the ICML, Vol. 119. PMLR.
- Nikaash Puri, Sukriti Verma, Piyush Gupta, Dhruv Kayastha, Shripad Deshmukh, Balaji Krishnamurthy, and Sameer Singh. 2020. Explain your move: Understanding agent actions using specific and relevant feature attribution. In Proceedings of the ICLR.
- Maithra Raghu, Justin Gilmer, Jason Yosinski, and Jascha Sohl-Dickstein. 2017. SVCCA: Singular vector canonical correlation analysis for deep learning dynamics and interpretability. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2017/hash/dc6a7e655d7e5840e66733e9ee67cc69-Abstract.html.
- Karthikeyan Natesan Ramamurthy, Bhanukiran Vinzamuri, Yunfeng Zhang, and Amit Dhurandhar. 2020. Model agnostic multilevel explanations. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/426f990b332ef8193a61cc90516c1245-Abstract.html.
- Kaivalya Rawal and Himabindu Lakkaraju. 2020. Beyond individualized recourse: Interpretable and interactive summaries of actionable recourses. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/8ee7730e97c67473a424ccfeff49ab20-Abstract.html.
- Laura Rieger, Chandan Singh, W. James Murdoch, and Bin Yu. 2020. Interpretations are useful: Penalizing explanations to align neural networks with prior knowledge. In Proceedings of the ICML, Vol. 119. PMLR.
- Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, and Enkelejda Kasneci. 2022. A consistent and efficient evaluation strategy for attribution methods. In Proceedings of the ICML, Vol. 162. PMLR.
- Benjamin Sanchez-Lengeling, Jennifer Wei, Brian Lee, Emily Reif, Peter Wang, Wesley Qian, Kevin McCloskey, Lucy Colwell, and Alexander Wiltschko. 2020. Evaluating attribution for graph neural networks. In Proceedings of the NeurIPS, Vol. 33. Curran Associates.
- Patrick Schwab and Walter Karlen. 2019. CXPlain: Causal explanations for model interpretation under uncertainty. In Proceedings of the NeurIPS.
- Wenxian Shi, Hao Zhou, Ning Miao, and Lei Li. 2020. Dispersed exponential family mixture VAEs for interpretable text generation. In Proceedings of the ICML, Vol. 119. PMLR.
- Chandan Singh, W. James Murdoch, and Bin Yu. 2019. Hierarchical interpretations for neural network predictions. In Proceedings of the ICLR.
- Sumedha Singla, Brian Pollack, Junxiang Chen, and Kayhan Batmanghelich. 2020. Explanation by progressive exaggeration. In Proceedings of the ICLR. OpenReview.net. Retrieved from https://openreview.net/forum?id=H1xFWgrFPS.
- Leon Sixt, Maximilian Granz, and Tim Landgraf. 2020. When explanations lie: Why many modified BP attributions fail. In Proceedings of the ICML, Vol. 119. PMLR. http://proceedings.mlr.press/v119/sixt20a.html.
- Mukund Sundararajan and Amir Najmi. 2020. The many shapley values for model explanation. In Proceedings of the ICML, Vol. 119. PMLR. Retrieved from http://proceedings.mlr.press/v119/sundararajan20b.html.
- Michael Tsang, Dehua Cheng, Hanpeng Liu, Xue Feng, Eric Zhou, and Yan Liu. 2020. Feature interaction interpretability: A case for explaining ad-recommendation systems via neural interaction detection. In Proceedings of the ICLR. OpenReview.net. Retrieved from https://openreview.net/forum?id=BkgnhTEtDS.
- Michael Tsang, Hanpeng Liu, Sanjay Purushotham, Pavankumar Murali, and Yan Liu. 2018. Neural interaction transparency (NIT): Disentangling learned interactions for improved interpretability. In Proceedings of the NeurIPS.
- Michael Tsang, Sirisha Rambhatla, and Yan Liu. 2020. How does this interaction affect me? Interpretable attribution for feature interactions. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/443dec3062d0286986e21dc0631734c9-Abstract.html.
- Ramakrishna Vedantam, Karan Desai, Stefan Lee, Marcus Rohrbach, Dhruv Batra, and Devi Parikh. 2019. Probabilistic neural symbolic models for interpretable visual question answering. In Proceedings of the ICML, Vol. 97. PMLR.
- Andrey Voynov and Artem Babenko. 2020. Unsupervised discovery of interpretable directions in the GAN latent space. In Proceedings of the ICML, Vol. 119. PMLR. Retrieved from http://proceedings.mlr.press/v119/voynov20a.html.
- Minh N. Vu and My T. Thai. 2020. PGM-explainer: Probabilistic graphical model explanations for graph neural networks. In Proceedings of the NeurIPS.
- Pei Wang and Nuno Vasconcelos. 2019. Deliberative explanations: Visualizing network insecurities. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2019/hash/68053af2923e00204c3ca7c6a3150cf7-Abstract.html.
- Shengjie Wang, Tianyi Zhou, and Jeff A. Bilmes. 2019. Bias also matters: Bias attribution for deep neural network explanation. In Proceedings of the ICML, Vol. 97. PMLR.
- Tong Wang. 2018. Multi-value rule sets for interpretable classification with feature-efficient representations. In Proceedings of the NeurIPS.
- Tong Wang. 2019. Gaining free or low-cost interpretability with interpretable partial substitute. In Proceedings of the ICML, Vol. 97. PMLR. Retrieved from http://proceedings.mlr.press/v97/wang19a.html.
- Andrew G. Wilson, Christoph Dann, Chris Lucas, and Eric P. Xing. 2015. The human kernel. In Proceedings of the NeurIPS, Vol. 28. Curran Associates, Inc. Retrieved from https://proceedings.neurips.cc/paper/2015/file/4462bf0ddbe0d0da40e1e828ebebeb11-Paper.pdf.
- Ning Xie Gabrielle Ras Marcel van Gerven and Derek Doran. 2020. Explainable deep learning: A field guide for the uninitiated. Retrieved from https://arXiv:2004.14545.
- Fan Yang Mengnan Du and Xia Hu. 2019. Evaluating explanation without ground truth in interpretable machine learning. Retrieved from https://arXiv:1907.06831.
- Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Sai Suggala, David I. Inouye, and Pradeep Ravikumar. 2019. On the (in)fidelity and sensitivity of explanations. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2019/hash/a7471fdc77b3435276507cc8f2dc2569-Abstract.html.
- Chih-Kuan Yeh, Been Kim, Sercan Ömer Arik, Chun-Liang Li, Tomas Pfister, and Pradeep Ravikumar. 2020. On completeness-aware concept-based explanations in deep neural networks. In Proceedings of the NeurIPS. Retrieved from https://proceedings.neurips.cc/paper/2020/hash/ecb287ff763c169694f682af52c1f309-Abstract.html.
- Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019. GNNExplainer: Generating explanations for graph neural networks. In Proceedings of the NeurIPS.
- Haizi Yu and Lav R. Varshney. 2017. Towards deep interpretability (MUS-ROVER II): Learning hierarchical representations of tonal music. In Proceedings of the ICLR. OpenReview.net. Retrieved from https://openreview.net/forum?id=ryhqQFKgl.
- Hao Zhang Jiayi Chen Haotian Xue and Quanshi Zhang. 2019. Towards a unified evaluation of explanation methods without ground truth. Retrieved from https://arXiv:1911.09017.
- Xin Zhang, Armando Solar-Lezama, and Rishabh Singh. 2018. Interpreting neural network judgments via minimal, stable, and symbolic corrections. In Proceedings of the NeurIPS.
- Yuan Zhao and Il Memming Park. 2016. Interpretable nonlinear dynamic modeling of neural trajectories. In Proceedings of the NeurIPS.
- Charles Y. Zheng, Francisco Pereira, Chris I. Baker, and Martin N. Hebart. 2019. Revealing interpretable object representations from human behavior. In Proceedings of the ICLR. OpenReview.net. Retrieved from https://openreview.net/forum?id=ryxSrhC9KX.
Cited by
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101805 · Cited by 1,762
Lekadir, K., Frangi, A. F., Porras, A. R., Glocker, B., Cintas, C., Langlotz, C. P., Weicken, E., Asselbergs, F. W., Prior, F., Collins, G. S., et al. (2025) · BMJ · doi:10.1136/bmj-2024-081554 · Cited by 957
Survey of Explainable AI Techniques in Healthcare
Chaddad, A., Peng, J., Xu, J., & Bouridane, A. (2023) · Sensors · doi:10.3390/s23020634 · Cited by 591
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Ser, J. D., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., et al. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102301 · Cited by 626
“In a recent survey on the evaluation of XAI, for instance, the authors identify several conceptual properties that should be considered to assess the quality of an explanation, and they propose quantitative evaluation methods to evaluate an explanation [212].”
BackgroundTowards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations
Rong, Y., Leemann, T., Nguyen, T.-T., Fiedler, L., Qian, P., Unhelkar, V., Seidel, T., Kasneci, G., & Kasneci, E. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3331846 · Cited by 278
“%) in [71]; Lower detection rate in [53] Biases in features used by models [57, 71] Moderate detection rate (50”
BackgroundMethodInfluentialPost-hoc vs ante-hoc explanations: xAI design guidelines for data scientists
Retzlaff, C. O., Angerschmid, A., Saranti, A., Schneeberger, D., Röttger, R., Müller, H., & Holzinger, A. (2024) · Cognitive Systems Research · doi:10.1016/j.cogsys.2024.101243 · Cited by 194
“As a central aspect of their work, Nauta et al. (2023) provide a classification of 12 essential explanation properties, including concepts such as Compactness and Correctness.”
InfluentialRecent Applications of Explainable AI (XAI): A Systematic Literature Review
Saarela, M., & Podgorelec, V. (2024) · Applied Sciences · doi:10.3390/app14198884 · Cited by 183
How Interpretable Machine Learning Can Benefit Process Understanding in the Geosciences
Jiang, S., Sweet, L., Blougouras, G., Brenning, A., Li, W., Reichstein, M., Denzler, J., Shangguan, W., Yu, G., Huang, F., et al. (2024) · Earth's Future · doi:10.1029/2024ef004540 · Cited by 182
“Several metrics have been developed to evaluate the suitability and effectiveness of interpretation techniques, focusing on comparing key properties between techniques for specific research problems (e.g., Hedström et al., 2024; Nauta et al., 2023).”
Retzlaff, C. O., Das, S., Wayllace, C., Mousavi, P., Afshari, M. P., Yang, T., Saranti, A., Angerschmid, A., Taylor, M. E., & Holzinger, A. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.15348 · Cited by 282
Adversarial attacks and defenses in explainable artificial intelligence: A survey
Baniecki, H., & Biecek, P. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102303 · Cited by 170
Shaping the future of AI in healthcare through ethics and governance
Bouderhem, R. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-02894-w · Cited by 162
“Providing explainable AI methods (Nauta et al. 2023) will allow for more transparency (Hassija et al. 2023) and accountability (Arrieta et al. 2020) for responsible AI systems.”
Interpretable and explainable machine learning: A methods‐centric overview with concrete examples
Marcinkevičs, R., & Vogt, J. E. (2023) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1493 · Cited by 161
“Nauta et al. (2022) provide the most comprehensive survey to date of qualitative and quantitative methods.”
BackgroundDai, E., Zhao, T., Zhu, H., Xu, J., Guo, Z., Liu, H., Tang, J., & Wang, S. (2024) · Machine Intelligence Research · doi:10.1007/s11633-024-1510-8 · Cited by 323
Mehrotra, S., Degachi, C., Vereschak, O., Jonker, C. M., & Tielman, M. L. (2024) · ACM Journal on Responsible Computing · doi:10.1145/3696449 · Cited by 254
Interpretability research of deep learning: A literature survey
Xu, B., & Yang, G. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102721 · Cited by 212
Explaining deep neural networks: A survey on the global interpretation methods
Saleem, R., Yuan, B., Kurugöllü, F., Anjum, A., & Liu, L. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.129 · Cited by 219
Human-centered evaluation of explainable AI applications: a systematic review
Kim, J., Maathuis, H., & Sent, D. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1456486 · Cited by 130
Explainable AI in Manufacturing and Industrial Cyber–Physical Systems: A Survey
Moosavi, S., Farajzadeh-Zanjani, M., Razavi‐Far, R., Palade, V., & Saif, M. (2024) · Electronics · doi:10.3390/electronics13173497 · Cited by 191
Explainable Predictive Maintenance: A Survey of Current Methods, Challenges and Opportunities
Cummins, L., Sommers, A., Ramezani, S. B., Mittal, S., Jabour, J. E., Seale, M. A., & Rahimi, S. (2024) · IEEE Access · doi:10.1109/access.2024.3391130 · Cited by 200
“While several researchers argue that the terms are synonymous, viewing them as interchangeable to simplify discussions [8], [9], [10], [11], others assert that they capture distinct concepts [12], [13], [14], [15], [16], [17], [18], [19].”
BackgroundExplainable AI approaches in deep learning: Advancements, applications and challenges
Hosain, M. T., Jim, J. R., Mridha, M. F., & Kabir, M. M. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109246 · Cited by 167
PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image Classification
Nauta, M., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00269 · Cited by 130
“Deep neural networks are dominant in computer vision, but there is a high demand for understanding the reasoning of such complex models [23,30].”
BackgroundSelf-citationSharma, K., Nguyen, A., & Hong, Y. (2024) · British Journal of Educational Technology · doi:10.1111/bjet.13459 · Cited by 192
Cybersecurity Revolution via Large Language Models and Explainable AI
Ghazal, T. M., Janjua, J. I., Abushiba, W., Ahmad, M., Ihsan, A., & Al-Dmour, N. A. (2024) · International Conference on Security of Information and Networks (SIN) · doi:10.1109/sin63213.2024.10871324 · Cited by 97
Steimers, A., & Schneider, M. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph19063641 · Cited by 149
“For example, the ongoing scientific discussion on the topic of XAI (explainable artificial intelligence) shows that this is one of the core problems of deep learning [59–61].”
BackgroundOpening the Black Box: A systematic review on explainable artificial intelligence in remote sensing
Höhl, A., Obadić, I., Fernández‐Torres, M., Najjar, H., Oliveira, D. A. B., Akata, Z., Dengel, A. R., & Zhu, X. X. (2024) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2024.3467001 · Cited by 141
Cobo, M., Fernández‐Miranda, P. M., Bastarrika, G., & Iglesias, L. L. (2023) · Scientific Data · doi:10.1038/s41597-023-02641-x · Cited by 88
Pawlicki, M., Pawlicka, A., Uccello, F., Szelest, S., D’Antonio, S., Kozik, R., & Choraś, M. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128282 · Cited by 89
Wang, Y., Wang, P., Tansey, K. J., Liu, J.-M., Delaney, B., & Quan, W. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109758 · Cited by 64
Agriculture 5.0 and Explainable AI for Smart Agriculture: A Scoping Review
Razak, A., Yogarayan, S., Sayeed, M. S., & Derafi, M. I. F. M. (2024) · Emerging Science Journal · doi:10.28991/esj-2024-08-02-024 · Cited by 91
“According to Nauta et al. [61], XAI methods can be evaluated based on goodness checklists, explanation satisfaction scales, elicitation methods for mental models, computational measures for explainer fidelity, explanation trustworthiness, and model reliability.”
MethodNascita, A., Aceto, G., Ciuonzo, D., Montieri, A., Persico, V., & Pescapè, A. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3504955 · Cited by 98
“In line with these efforts, in Table V we have also provided a “translation” of the adopted terms and the corresponding ones used in the systematic organization presented in [4].”
InfluentialVisser, R., Peters, T. M., Scharlau, I., & Hammer, B. (2025) · Cognitive Systems Research · doi:10.1016/j.cogsys.2025.101357 · Cited by 58
“Notably, Zhou et al. (2021) refer to fidelity and faithfulness as being the same concept, whereas Nauta et al. (2022) use the term correctness to reflect an explanations faithfulness with respect to the underlying model while Zhou et al. (2021) use the term soundness to refer to the correctness of…”
Toward precision interventions and metrics of inflammaging
Franceschi, C., Olivieri, F., Moskalev, A., Ivanchenko, M., & Santoro, A. (2025) · Nature Aging · doi:10.1038/s43587-025-00938-7 · Cited by 71
Erdur, A. C., Rusche, D., Scholz, D., Kiechle, J., Fischer, S. M., Llorián-Salvador, Ó., Buchner, J. A., Nguyen, M. Q., Etzel, L., Weidner, J., et al. (2024) · Strahlentherapie und Onkologie · doi:10.1007/s00066-024-02262-2 · Cited by 86
“This is achieved by disclosing its reasoning, functioning, or behavior in human-understandable terms [41–43].”
Anomaly and intrusion detection using deep learning for software-defined networks: A survey
Ruffo, V. G. D. S., Lent, D. M. B., Komarchesqui, M., Schiavon, V. F., de Assis, M. V. O., Carvalho, L. F., & Proença, M. L. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124982 · Cited by 77
Current status and future directions of explainable artificial intelligence in medical imaging
Saw, S. N., Yan, Y. Y., & Ng, K. H. (2024) · European Journal of Radiology · doi:10.1016/j.ejrad.2024.111884 · Cited by 79
Gongane, V. U., Munot, M. V., & Anuse, A. D. (2024) · Journal of Computational Social Science · doi:10.1007/s42001-024-00248-9 · Cited by 90
eXplainable Artificial Intelligence (XAI) in aging clock models
Kalyakulina, A., Yusipov, I., Moskalev, A., Franceschi, C., & Ivanchenko, M. (2023) · Ageing Research Reviews · doi:10.1016/j.arr.2023.102144 · Cited by 48
“, 2014], and made eXplainable Artificial Intelligence (XAI) an important area of AI [Nauta et al., 2023].”
Naveed, S., Stevens, G., & Robin-Kern, D. (2024) · Applied Sciences · doi:10.3390/app142311288 · Cited by 88
Explainable Artificial Intelligence for Medical Applications: A Review
Sun, Q., Akman, A., & Schuller, B. W. (2024) · ACM Transactions on Computing for Healthcare · doi:10.1145/3709367 · Cited by 140
“Although frameworks such as the Co-12 properties [129] offer a structured foundation for explainability evaluation, their adoption remains limited in medical contexts.”
Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant
He, G., Aishwarya, N., & Gadiraju, U. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708359.3712133 · Cited by 115
“For a more comprehensive review of existing XAI methods and criteria to evaluate XAI methods, we encourage readers to refer to recent work by Arrieta et al. [2], Nauta et al. [80].”
A quantitative approach for the comparison of additive local explanation methods
Doumard, E., Aligon, J., Escriva, E., Excoffier, J.-B., Monsarrat, P., & Soulé-Dupuy, C. (2022) · Information Systems · doi:10.1016/j.is.2022.102162 · Cited by 59
Human attention guided explainable artificial intelligence for computer vision models
Liu, G., Zhang, J., Chan, A. B., & Hsiao, J. H. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106392 · Cited by 57
Bloch, L., & Friedrich, C. M. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108029 · Cited by 48
Moreno-Sánchez, P. A., Ser, J. D., van Gils, M., & Hernesniemi, J. A. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103812 · Cited by 77
Geyer, P., Singh, M. M., & Chen, X. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102843 · Cited by 63
A Missing Piece in the Puzzle: Considering the Role of Task Complexity in Human-AI Decision Making
Salimzadeh, S., He, G., & Gadiraju, U. (2023) · Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization · doi:10.1145/3565472.3592959 · Cited by 42
“User factors like expertise [28], machine learning literacy [24], and task characteristics like task subjectivity and proximity [15], and task types [34, 49, 55, 61, 74] have also been broadly investigated.”
BackgroundSalimzadeh, S., He, G., & Gadiraju, U. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641905 · Cited by 41
“Some prior works have also provided a taxonomy of task types existing in the literature [1, 92].”
BackgroundAbdelaal, Y., Aupetit, M. J. M., Baggag, A., & Al‐Thani, D. (2024) · Journal of Medical Internet Research · doi:10.2196/53863 · Cited by 60
“This trend aligns with findings in the broader literature, where only 1 in 5 papers included user evaluations [26].”
InfluentialBrankovic, A., Cook, D., Rahman, J., Delaforce, A., Li, J., Magrabi, F., Cabitza, F., Coiera, E., & Bradford, D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01764-2 · Cited by 37
“Nauta et al. 14 provided an extensive overviewof quantitative XAI evaluation methods used in the XAI literature and identi fi es 12 properties to evaluate explanations without user studies.”
InfluentialChuan, C., Sun, R., Tian, S., & Tsai, W. S. (2024) · Telematics and Informatics · doi:10.1016/j.tele.2024.102135 · Cited by 63
Deep 3D histology powered by tissue clearing, omics and AI
Ertürk, A. (2024) · Nature Methods · doi:10.1038/s41592-024-02327-1 · Cited by 45
“Despite substantial research efforts 122 , complete solutions for the increasingly complex models are still lacking.”
Rajpura, P., Cecotti, H., & Meena, Y. K. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad6593 · Cited by 58
“A noteworthy interest in decoding motor imagery and”
Xu, L., Ning, S., Xu, X., Wang, S., Chen, L., Long, R., Zhang, S., Zhou, Y., Zhang, M., & Thapa, B. R. (2024) · Agricultural Water Management · doi:10.1016/j.agwat.2024.109176 · Cited by 43
Explainable Artificial Intelligence: Importance, Use Domains, Stages, Output Shapes, and Challenges
Ullah, N., Khan, J. A., Falco, I. D., & Sannino, G. (2024) · ACM Computing Surveys · doi:10.1145/3705724 · Cited by 87
The Role of Human Knowledge in Explainable AI
Tocchetti, A., & Brambilla, M. (2022) · Data · doi:10.3390/data7070093 · Cited by 55
“On such a topic, while a variety of evaluation methods and approaches have been proposed [63], it is still argued that the best way to assess the interpretability of black-box models is through user experiments and user-centred evaluations as there is no guarantee for the correctness of automated…”
BackgroundAdversarial Attacks in Explainable Machine Learning: A Survey of Threats Against Models and Humans
Vadillo, J., Santana, R., & Lozano, J. A. (2024) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1567 · Cited by 59
Uncertainty in XAI: Human Perception and Modeling Approaches
Chiaburu, T., Haußer, F., & Bießmann, F. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6020055 · Cited by 53
“Despite decades of research and a growing body of literature [22,29,54–57], the evaluation of XAI methods remains to this day a subject of active research.”
BackgroundGuo, R., Wei, J., Sun, L., Yu, B., Chang, G., Liu, D., Zhang, S., Yao, Z., Xu, M., & Bu, L. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108709 · Cited by 69
“• Indicators and Evaluation Techniques for Inter-pretability : Developing metrics and evaluation frameworks that can quantitatively assess a model’s inter-pretability and transparency [157].”
BackgroundMehdiyev, N., Majlatow, M., & Fettke, P. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11399-0 · Cited by 61
Nicolson, A., Bradburn, E., Gal, Y., Papageorghiou, A. T., & Noble, J. A. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02023-0 · Cited by 56
Benchmarking eXplainable AI - A Survey on Available Toolkits and Open Challenges
Le, P. Q., Nauta, M., Nguyen, V. B., Pathak, S., Schlötterer, J., & Seifert, C. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/747 · Cited by 60
Self-citationA Comparative Study and Systematic Analysis of XAI Models and their Applications in Healthcare
Gupta, J., & Seeja, K. R. (2024) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-024-10103-9 · Cited by 62
Nguyen, B., & Chioua, M. (2024) · Control Engineering Practice · doi:10.1016/j.conengprac.2024.105988 · Cited by 34
Unsupervised Representation Learning in Deep Reinforcement Learning: A Review
Botteghi, N., Poel, M., & Brüne, C. (2025) · IEEE Control Systems · doi:10.1109/mcs.2025.3534477 · Cited by 57
Tempel, F., Ihlen, E. A. F., Adde, L., & Strümke, I. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.109838 · Cited by 39
“This reliance highlights the need for quantitative metrics to objectively evaluate explanation methods beyond what visual and qualitative assessments alone can deliver [17].”
Explainable AI: To Reveal the Logic of Black-Box Models
Chinu, & Bansal, U. (2023) · New Generation Computing · doi:10.1007/s00354-022-00201-2 · Cited by 39
“M. Nauta et al. [101] have divided the evaluation criteria into three classes: content level, user level, and explanation level.”
Enhancing Transparency in Smart Farming: Local Explanations for Crop Recommendations Using LIME
Akkem, Y., Biswas, S. K., Aruna, V., & Tripathi, D. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.450 · Cited by 35
Explainable vision transformer for automatic visual sleep staging on multimodal PSG signals
Lee, H., Choi, Y. R., Lee, H. K., Jeong, J., Hong, J., Shin, H., & Kim, H. (2025) · npj Digital Medicine · doi:10.1038/s41746-024-01378-0 · Cited by 27
“To mitigate this, we assessed SleepXViT ’ s explainability by examining the consistency of its explanations across similar inputs, following the principle that similar inputs should yield similar explanations 50 .”
Evaluating the effectiveness of XAI techniques for encoder-based language models
Mersha, M. A., Yigezu, M. G., & Kalita, J. K. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113042 · Cited by 35
Morey, D. A., Rayo, M. F., & Woods, D. D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01784-y · Cited by 35
“First, empirical evaluations of AI explanations which involve domain practitioners are rare 15 .”
A comparative evaluation of explainability techniques for image data
Skliarov, M., Shawi, R. E., Dhaoui, C., & Ahmed, N. M. O. S. (2025) · Scientific Reports · doi:10.1038/s41598-025-25839-y · Cited by 43
Teoh, Y. X., Othmani, A., Goh, S. L., Usman, J., & Lai, K. W. (2024) · IEEE Access · doi:10.1109/access.2024.3439096 · Cited by 31
“As high-lighted by Nauta et al. [45], it is important to recognize that certain explanation methods have the ability to incorporate multiple types of explanations, thereby making the categories of explanation methods non-mutually exclusive.”
BackgroundMethodInfluentialKlug, K., Beckh, K., Antweiler, D., Chakraborty, N., Baldini, G., Laue, K., Hosch, R., Nensa, F., Schüler, M., & Giesselbach, S. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02641-w · Cited by 32
“Anecdotal evidence is common and a fundamental flaw in the field [54].”
BackgroundHasan, M., Vasker, N., & Khan, M. (2024) · Journal of Agriculture and Food Research · doi:10.1016/j.jafr.2024.101372 · Cited by 27
Explainability and vision foundation models: A survey
Kazmierczak, R., Berthier, É., Frehse, G., & Franchi, G. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103184 · Cited by 61
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods
Hesse, R., Schaub-Meyer, S., & Roth, S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00368 · Cited by 75
Which LIME Should I Trust? Concepts, Challenges, and Solutions
Knab, P., Marton, S., Schlegel, U., & Bartelt, C. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08324-1_2 · Cited by 57
Aliyeva, K. R., & Mehdiyev, N. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119987 · Cited by 31
Guo, T., Bardhan, I. R., Ding, Y., & Zhang, S. (2024) · Information Systems Research · doi:10.1287/isre.2023.0029 · Cited by 28
Folgado, D., Barandas, M., Famiglini, L., Santos, R., Cabitza, F., & Gamboa, H. F. S. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101955 · Cited by 28
Literature Review of Explainable Tabular Data Analysis
Quinn, H. O., Sedky, M., Francis, J., & Streeton, M. (2024) · Electronics · doi:10.3390/electronics13193806 · Cited by 30
“Nauta et al. viewed explanation assessment as a twelve-faceted problem and developed a twelve-property quality evaluation [27].”
Causality and scientific explanation of artificial intelligence systems in biomedicine
Boge, F. J., & Mosig, A. (2024) · Pflügers Archiv - European Journal of Physiology · doi:10.1007/s00424-024-03033-9 · Cited by 31
Ndao, M. L., Youness, G., Niang, N., & Saporta, G. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110144 · Cited by 27
Aligning generalization between humans and machines
Ilievski, F., Hammer, B., van Harmelen, F., Paaßen, B., Saralajew, S., Schmid, U., Biehl, M. L., Bolognesi, M., Dong, X., Gashteovski, K., et al. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01109-4 · Cited by 57
“The explicit knowledge use allows testing a model’s explainable predictions through human studies and faithfulness evaluation 115 .”
Chun, J., & Elkins, K. (2023) · International Journal of Digital Humanities · doi:10.1007/s42803-023-00069-8 · Cited by 31
“Alongside progress in low/no-code AI tools like RapidMiner and Keras, XAI has evolved from a focus on largely technical considerations to include more human-centered issues (Nauta et al., 2022).”
The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers
Nauta, M., & Seifert, C. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44064-9_21 · Cited by 30
Self-citationExplainable AI (XAI) In Biomedical Signal and Image Processing: Promises and Challenges
Yang, G., Rao, A., Fernandez-Maloigne, C., Calhoun, V., & Menegaz, G. (2022) · 2022 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip46576.2022.9897629 · Cited by 18
“An extended taxonomy can be found in [26] where twelve explanation quality properties, grouped by their most prominent dimension, that is Content, Presentation or User, are proposed.”
BackgroundLai, X., Lai, Y., Chen, J., Huang, S., Gao, Q., & Huang, C. (2025) · Journal of Medical Internet Research · doi:10.2196/79217 · Cited by 30
Sokol, K., & Vogt, J. E. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3651047 · Cited by 35
Fresz, B., Dubovitskaya, E., Brajovic, D., Huber, M. F., & Horz, C. (2024) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1609/aies.v7i1.31648 · Cited by 17
“In this work, the taxonomy of Nauta et al. (2023) is used, as an explorative literature research rendered it the most complete and comprehensive.”
Liu, W., Karagoz, G. N., & Meratnia, N. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make7010001 · Cited by 31
Maathuis, C., Cidota, M. A., Datcu, D., & Marin, L. (2025) · Mathematics · doi:10.3390/math13020290 · Cited by 23
Wardatzky, K., Inel, O., Rossetto, L., & Bernstein, A. (2025) · ACM Transactions on Recommender Systems · doi:10.1145/3716394 · Cited by 35
Cerasuolo, F., Bovenzi, G., Ciuonzo, D., & Pescapè, A. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111228 · Cited by 22
Rietberg, M. T., Nguyen, V. B., Geerdink, J., Vijlbrief, O., & Seifert, C. (2023) · Diagnostics · doi:10.3390/diagnostics13071251 · Cited by 17
Self-citationAn interdisciplinary perspective on AI-supported decision making in medicine
Ammeling, J., Aubreville, M., Fritz, A., Kießig, A., Krügel, S., & Uhl, M. (2024) · Technology in Society · doi:10.1016/j.techsoc.2024.102791 · Cited by 22
Explainable Machine Learning in Risk Management: Balancing Accuracy and Interpretability
Wang, M., Zhang, X., Yang, Y., & Wang, J. (2025) · Journal of Financial Risk Management · doi:10.4236/jfrm.2025.143011 · Cited by 22
Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking
Warren, G., Shklovski, I., & Augenstein, I. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713277 · Cited by 66
“Various desiderata for explanations of AI systems have been proposed in recent years [70, 86, 105].”
Mechanistic understanding and validation of large AI models with SemanticLens
Dreyer, M., Berend, J., Labarta, T., Vielhaben, J., Wiegand, T., Lapuschkin, S., & Samek, W. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01084-w · Cited by 48
“These include the need to adopt meaningful evaluation metrics 51 , to adapt to generative models 52 and to address the limitations of ‘post hoc’ versus ‘ante hoc’ interpretability 53 .”
Toward explainable artificial intelligence: A survey and overview on their intrinsic properties
Mi, J., Jiang, X., Luo, L., & Gao, Y. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126919 · Cited by 27
Metadata
- Authors
- Nauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C.
- Affiliations
- University of Duisburg-Essen (DE)
- University of Twente (NL)
- University of Twente, the Netherlands
- ORCID
- Venue
- ACM Computing Surveys
- Published
- 2023-07-13
- Volume
- 55
- Issue
- 13s
- Pages
- 1-42
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4321786089
- Cited by
- 590
- References
- 202
- Citations by year
- 2026: 184 · 2025: 195 · 2024: 157 · 2023: 45
- FWCI
- 12.16
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Computing Surveys (publishedVersion, cc-by)
- arXiv (Cornell University) (publishedVersion)
- University of Twente Research Information (publishedVersion, other-oa)
- University of Twente Research Information (submittedVersion, other-oa)
- arXiv (Cornell University) (cc-by)
- Funders
- Ziekenhuis Groep Twente
- 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, XAI evaluation, explanation quality metrics, interpretability, quantitative evaluation methods, anecdotal evidence, user evaluation, benchmarking, black-box models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (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.