From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
Open accessThe 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.
Abstract
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
Items 101–200 of 592
Ailey, S. H., Bathje, M., Tichá, R., Abery, B. H., Khuu, B. P., & Angel, L. (2024) · Journal of Applied Research in Intellectual Disabilities · doi:10.1111/jar.13208 · Cited by 27
Ghanvatkar, S., & Rajan, V. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3393719 · Cited by 22
“While there are metrics to evaluate faithfulness, to our knowledge, there are no automated metrics to evaluate the usefulness of explanations in the clinical context.”
BackgroundEvaluating Explainable Machine Learning Models for Clinicians
Scarpato, N., Nourbakhsh, A., Ferroni, P., Riondino, S., Roselli, M., Fallucchi, F., Barbanti, P., Guadagni, F., & Zanzotto, F. M. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10297-x · Cited by 22
“It is essential tooffer andevaluate an explanation model for a more obscure but fairly accurate MLBP as better-performing models are usually harder to explain [30, 31].”
Dreyer, M., Achtibat, R., Samek, W., & Lapuschkin, S. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00353 · Cited by 42
“One of the most popular evaluation methods to check an explanation’s faithfulness to the model is to perform feature deletion [36].”
Kundu, R. K., & Hoque, K. A. (2023) · Annual Conference of the PHM Society · doi:10.36001/phmconf.2023.v15i1.3472 · Cited by 19
“The researchers have proposed several metrics to measure the explainability of AI models (Elkhawaga, Elzeki, Abuelkheir, & Reichert, 2023; Nauta et al., 2023).”
BackgroundOn the multiple roles of ontologies in explanations for neuro-symbolic AI
Confalonieri, R., & Guizzardi, G. (2024) · Neurosymbolic Artificial Intelligence · doi:10.3233/nai-240754 · Cited by 31
“In [51], the authors identify several conceptual properties that should be considered to assess the quality of explanations, and they propose quantitative evaluation methods to evaluate an explanation.”
dos Reis, M. Í., Gonçalves, J. N. C., Cortez, P. C., Carvalho, M. S., & Fernandes, J. M. (2024) · Computers in Industry · doi:10.1016/j.compind.2024.104233 · Cited by 26
Chan, Y. H., Girish, D., Gupta, S., Xia, J., Kasi, C., He, Y., Wang, C., & Rajapakse, J. C. (2025) · NeuroImage · doi:10.1016/j.neuroimage.2025.121422 · Cited by 24
Suffian, M., Kuhl, U., Bogliolo, A., & Alonso-Moral, J. M. (2025) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2025.103484 · Cited by 19
Gangwal, A., & Lavecchia, A. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100943 · Cited by 23
From Black Boxes to Conversations: Incorporating XAI in a Conversational Agent
Nguyen, V. B., Schlötterer, J., & Seifert, C. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44070-0_4 · Cited by 39
“To further filter the candidate set for XAI methods to incorporate in conversational agents, we defined the following four criteria for our analysis, the latter three based on the categorization scheme of a recent survey [36], which identified 312 original papers, presenting a novel XAI technique in one of the major M…”
MethodSelf-citationLongo, L., Brčić, M., Cabitza, F., Choi, J., Confalonieri, R., Ser, J. D., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.19775 · Cited by 14
“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].”
BackgroundAI assistance in enterprise UX design workflows: enhancing design brief creation for designers
Zhu, Z., Lee, H., Cai, P., & Pan, Y. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1404647 · Cited by 35
Fewer Than 1% of Explainable AI Papers Validate Explainability with Humans
Suh, A., Hurley, I., Smith, N., & Siu, H. C. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3719964 · Cited by 37
Saliency-Bench: A Comprehensive Benchmark for Evaluating Visual Explanations
Zhang, Y., Song, J., Gu, S., Jiang, T., Pan, B., Bai, G., & Zhao, L. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737414 · Cited by 27
How Explainable Is Explainability? Towards Better Metrics for Explainable AI
Pawlicka, A., Pawlicki, M., Kozik, R., Kurek, W., & Choraś, M. (2023) · Springer proceedings in complexity · doi:10.1007/978-3-031-44721-1_52 · Cited by 14
Explainable AI: Machine Learning Interpretation in Blackcurrant Powders
Przybył, K. (2024) · Sensors · doi:10.3390/s24103198 · Cited by 16
“In turn, having the structure of the data, machine learning algorithms make decisions on the basis of ‘glass box’ and ‘black box’ [31–33].”
BackgroundBEExAI: Benchmark to Evaluate Explainable AI
Sithakoul, S., Meftah, S., & Feutry, C. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63787-2_23 · Cited by 26
Shi, H., Xu, T., Li, X., Gao, Q., Xiong, Z., Xia, J., & Yue, Z. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103101 · Cited by 16
“While increasing research focuses on interpretability evaluation [48, 49], an evaluation framework for explaining bipartite network interactions remained underdeveloped.”
Deploying explainable AI in entrepreneurial organizations: Role of the human-AI interface
Chaudhary, S., Khalil, A., Attri, R., & Ractham, P. (2025) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2025.124324 · Cited by 17
Roychowdhury, S., Lanfranchi, V., & Mazumdar, S. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110944 · Cited by 21
VISUAL STORYTELLING AND EXPLAINABLE INTELLIGENCE IN ORGANIZATIONAL CHANGE COMMUNICATION
Kashyap, S., Purohit, S., Kumar, A., Jawaid, F. I. M., Kumar, J. R. R., & Ajani, S. N. (2025) · ShodhKosh Journal of Visual and Performing Arts · doi:10.29121/shodhkosh.v6.i5s.2025.6965 · Cited by 13
T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers
Ntrougkas, M. V., Gkalelis, N., & Mezaris, V. (2024) · IEEE Access · doi:10.1109/access.2024.3405788 · Cited by 13
“This new evaluation protocol has been adopted in the very recent works [52], [53].”
MethodPrototype-Based Interpretable Breast Cancer Prediction Models: Analysis and Challenges
Pathak, S., Schlötterer, J., Veltman, J., Geerdink, J., van Keulen, M., & Seifert, C. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63787-2_2 · Cited by 12
Self-citationGokhale, G., Madahi, S. S. K., Claessens, B., & Develder, C. (2024) · ACM International Conference on Future Energy Systems (e-Energy) · doi:10.1145/3632775.3661937 · Cited by 25
“From this table, it can be clearly observed that the proposed DDTs have a significantly smaller compute footprint due to the reduced number of parameters, leading to trained models which are about 200 times smaller than the teacher DQN agents.”
BackgroundTertiary Review on Explainable Artificial Intelligence: Where Do We Stand?
van Mourik, F., Jutte, A., Berendse, S. E., Bukhsh, F. A., & Ahmed, F. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6030098 · Cited by 19
Exploring LLM-Driven Explanations for Quantum Algorithms
d’Aloisio, G., Fortz, S., Hanna, C., Fortunato, D., Bensoussan, A., Usandizaga, E. M., & Sarro, F. (2024) · Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement · doi:10.1145/3674805.3690753 · Cited by 26
SIDU-TXT: An XAI algorithm for NLP with a holistic assessment approach
Jahromi, M. N. S., Muddamsetty, S. M., Jarlner, A. S. S., Høgenhaug, A. M., Gammeltoft‐Hansen, T., & Moeslund, T. B. (2024) · Natural Language Processing Journal · doi:10.1016/j.nlp.2024.100078 · Cited by 15
Velmurugan, M., Ouyang, C., Xu, Y., Sindhgatta, R., Wickramanayake, B., & Moreira, C. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109772 · Cited by 18
Kozielski, M., Sikora, M., & Wawrowski, Ł. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113092 · Cited by 15
“Confidence (Confidence measure of the explanation or model output) is a property that can take into account two components [60].”
BackgroundMethodInfluentialHow digital twin technology may improve safety management: A multi-industry perspective
Zou, P. X. W., & Ma, S. (2025) · Safety Science · doi:10.1016/j.ssci.2025.106837 · Cited by 16
Xie, J., Qin, Y., Zhang, Y., Li, J., Chen, T., Zhao, X., & Xia, Y. (2025) · Accident Analysis & Prevention · doi:10.1016/j.aap.2025.108037 · Cited by 13
Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future
Wu, S., Jiang, O., Zhao, Y., Hu, T., Ma, Y., Zhang, K., Patwardhan, M., & Cohan, A. (2026) · Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.acl-long.1504 · Cited by 11
Lago, M. A., Zamzmi, G., Eich, B., & Delfino, J. G. (2026) · Bioengineering · doi:10.3390/bioengineering13010111 · Cited by 22
“Additional methods include the Single Deletion Method and the Incremental Deletion Method [28,29].”
Xue, Q., Zhu, B., Li, Z., Tang, Y., & Wang, Y. (2026) · Food Chemistry · doi:10.1016/j.foodchem.2026.148062 · Cited by 10
Explainable time-series forecasting with sampling-free SHAP for Transformers
Hertel, M., Pütz, S., Mikut, R., Hagenmeyer, V., & Schäfer, B. (2026) · Nature Communications · doi:10.1038/s41467-026-73243-5 · Cited by 17
“We view this evaluation approach as complementary to existing explanation metrics 59 and believe that it can be extended to other data modalities in the future.”
Beenhakker, L., Wijlens, K. A. E., Witteveen, A., Heins, M. J., Korevaar, J. C., de Ligt, K. M., Bode, C., Vollenbroek-Hutten, M. M. R., & Siesling, S. (2023) · Journal of Cancer Survivorship · doi:10.1007/s11764-023-01491-1 · Cited by 13
“Also, the models should be explainable to both the clinician and the patient [53].”
Towards Directive Explanations: Crafting Explainable AI Systems for Actionable Human-AI Interactions
Bhattacharya, A. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3638177 · Cited by 19
“More recently, many researchers have questioned the efficacy of current quantitative user-centric metrics to compare different XAI methods [3, 28, 35].”
Diverse explanations from data-driven and domain-driven perspectives in the physical sciences
Li, S., Wang, X., & Barnard, A. S. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad9137 · Cited by 18
“Feature-based explanations play a crucial role in interpreting model behavior in human-understandable terms [1, 26, 38–40].”
Towards Visual Analytics for Explainable AI in Industrial Applications
Kucher, K., Zohrevandi, E., & Westin, C. (2025) · Analytics · doi:10.3390/analytics4010007 · Cited by 17
“Nauta et al. provide the following definition for such AI/ML scenarios: “An explanation is a presentation of (aspects of) the reasoning, functioning and/or behavior of a machine learning model in human-understandable terms” [26].”
InfluentialGanie, S. M., & Pramanik, P. K. D. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108438 · Cited by 12
Alam, K. N., Zadeh, P. B., & Sheikh-Akbari, A. (2025) · Electronics · doi:10.3390/electronics14153024 · Cited by 15
Pudney, S., Mills, D., Alaei, A., Sellers, S., Dvořák, J., & Potluka, O. (2025) · Evaluation · doi:10.1177/13563890251350677 · Cited by 18
“Nauta et al. (2023) proposed 12 conceptual properties of explainability arising from a review of 312 AI explainability studies, each of which depicts the evaluation of an explaina-bility method.”
An Overview and Comparison of XAI Methods for Object Detection in Computer Tomography
Sahatova, K., & Balabaeva, K. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.11.005 · Cited by 14
Bayrak, B., & Bach, K. (2024) · IEEE Access · doi:10.1109/access.2024.3410540 · Cited by 19
“This metric has found application in various articles [2], [8], [15], [18], [34], [49], [50] which are implemented similar to Equation 13.”
BackgroundMethodInfluentialAn Advanced Explainable Belief Rule-Based Framework to Predict the Energy Consumption of Buildings
Kabir, S., Hossain, M. S., & Andersson, K. (2024) · Energies · doi:10.3390/en17081797 · Cited by 11
“For explainability level (crisp value between 0 and 1), antecedent attributes have five ex-plainability evaluation metrics: feature coverage, relevance [47], test–retest reliability [48], coherence [49], and difference between explanation logic and model logic [50].”
BackgroundMethodAre Large Language Models the New Interface for Data Pipelines?
Barbon, S., Ceravolo, P., Groppe, S., Jarrar, M., Maghool, S., Sèdes, F., Sahri, S., & van Keulen, M. (2024) · International Workshop on Big Data in Emergent Distributed Environments (BiDEDE) · doi:10.1145/3663741.3664785 · Cited by 12
On the Way to a Transparent HRI
Rossi, A., & Rossi, S. (2024) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3631700.3664890 · Cited by 14
Explanatory Capabilities of Large Language Models in Prescriptive Process Monitoring
Kubrak, K., Botchorishvili, L., Milani, F., Nolte, A., & Dumas, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70396-6_23 · Cited by 19
“Another study utilized SHAP values to explain predictions in ongoing cases at run-time [11].”
Explainable machine learning by SEE-Net: closing the gap between interpretable models and DNNs
Seo, B., & Li, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-77507-2 · Cited by 16
Prashanthan, A., Roshan, R., & Maduranga, M. (2025) · Journal of Future Artificial Intelligence and Technologies · doi:10.62411/faith.3048-3719-110 · Cited by 12
Explainable few-shot learning workflow for detecting invasive and exotic tree species
Gevaert, C. M., Pedro, A. A., Ku, O., Cheng, H., Chandramouli, P., Javan, F. D., Nattino, F., & Georgievska, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-05394-2 · Cited by 10
“We utilize the Co-12 concepts proposed in 32 to evaluate the explanation provided.”
Lyberatos, V., Kontos, G., Spanos, N., Mastromichalakis, O. M., Voulodimos, A. S., & Stamou, G. B. (2026) · AI · doi:10.3390/ai7030095 · Cited by 14
The Blame Problem in Evaluating Local Explanations and How to Tackle It
Rahnama, A. H. A. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-50396-2_4 · Cited by 9
Clark, B., Wilming, R., & Haufe, S. (2024) · Machine Learning · doi:10.1007/s10994-024-06574-3 · Cited by 20
“Other work in the field tends to focus on secondary criteria (such as stability and robustness (Rosenfeld et al., 2021; Hedström et al., 2022)) or subjective or potentially circular criteria (such as fidelity and faithfulness (Gevaert et al., 2022; Nauta et al., 2023)).”
BackgroundVanNostrand, P. M., Hofmann, D. M., Ma, L., & Rundensteiner, E. A. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658997 · Cited by 26
Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations
Frész, B., Lörcher, L., & Huber, M. F. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658537 · Cited by 13
“An overview of the methods published by the end of 2020 can be found in [24].”
BackgroundMethodMouhamadou Lamine, N. D. A. O., Youness, G., Niang, N., & Saporta, G. (2024) · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference · doi:10.32473/flairs.37.1.135526 · Cited by 10
“Each of these metrics evaluates a specific property (Nauta et al. 2023).”
BackgroundPart-Prototype Models in Medical Imaging: Applications and Current Challenges
Santi, L. A. D., Piparo, F. I., Bargagna, F., Santarelli, M. F., Celi, S., & Positano, V. (2024) · BioMedInformatics · doi:10.3390/biomedinformatics4040115 · Cited by 13
A Comprehensive User-Centric Method for Evaluating and Comparing XAI Explanations
Brdnik, S., Karakatič, S., & Šumak, B. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2470278 · Cited by 10
“The evaluation of XAI systems is one of the more widely recognized challenges in the field of XAI (Haque et al., 2023; Nazar et al., 2021; Neto et al., 2022; Nauta et al., 2023).”
Measuring Online Hate on 4chan Using Pre-Trained Deep Learning Models
Bermudez-Villalva, A., Mehrnezhad, M., & Toreini, E. (2025) · IEEE Transactions on Technology and Society · doi:10.1109/tts.2025.3549931 · Cited by 11
“In the absence of true labels for the dataset, an intrinsic evaluation was conducted to assess the behaviour and performance of the model [37], [38].”
Ganie, S. M., Pramanik, P. K. D., & Zhao, Z. (2025) · Scientific Reports · doi:10.1038/s41598-025-20936-4 · Cited by 14
“XAI comprises techniques that enhance the transparency and interpretability of AI models, ensuring their decisions are understandable to human experts 60 essential for making models trustworthy and practical in healthcare.”
Agwu, O. E., Alatefi, S., & Alkouh, A. B. (2025) · Case Studies in Thermal Engineering · doi:10.1016/j.csite.2025.107459 · Cited by 11
Performance Measurements in the AI-Centric Computing Continuum Systems
Donta, P. K., Zhang, Q., & Dustdar, S. (2025) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot64238.2025.11270701 · Cited by 8
“(3). where, N is the total number of nodes, γ i is the weight for node i , and is the local explainability score of node i , and it depend on various factors [21] whereas our formule considered Fi-delity Robustness R = sim ϕ ( x ) , ϕ ( x + ϵ ) .”
Felizzato, G., Bagnulo, E., Tapparo, G., Botta, G., Cordero, C. E. I., Liberto, E., & Caratti, A. (2026) · Journal of Chromatography A · doi:10.1016/j.chroma.2026.467176 · Cited by 12
“In particular, there is no universally accepted framework for validating and evaluating explanations, unlike predictive models, which rely on standard performance metrics [58,59].”
Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment
Zhao, T., Luo, D., Zhang, X. D., & Wang, S. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3616542 · Cited by 13
“Different explanations obtained by GNNExplainer break the criteria of consistency , i.e., the explanation method should be deterministic and consistent with the same input for different runs [26].”
BackgroundHolm, S., & Macedo, L. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44064-9_31 · Cited by 11
Current Trends, Challenges and Techniques in XAI Field; A Tertiary Study of XAI Research
Brdnik, S., & Šumak, B. (2024) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro60963.2024.10569528 · Cited by 21
iSee: A case-based reasoning platform for the design of explanation experiences
Caro-Martínez, M., Recio-García, J. A., Díaz-Agudo, B., Darias, J. M., Wiratunga, N., Martin, K., Wijekoon, A., Nkisi-Orji, I., Corsar, D., Pradeep, P., et al. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112305 · Cited by 16
“For example, there are published reviews, e.g. [ 32], and there are several recent evaluation frameworks, e.g. [ 33,34].”
Thomas, D., Li, Y., Ukwuoma, C. C., & Dossa, J. V. (2024) · Social Science & Medicine · doi:10.1016/j.socscimed.2024.117329 · Cited by 8
Fayyad, M. F., & Mustakim, M. (2024) · International Electronics Symposium (IES) · doi:10.1109/ies63037.2024.10665856 · Cited by 12
“According to Nauta et al. (2023), evaluation metrics are used to estimate the performance of predictive models [46].”
MethodT-Explainer: A Model-Agnostic Explainability Framework Based on Gradients
Ortigossa, E. S., Dias, F. F., Barr, B., Silva, C. T., & Nonato, L. G. (2025) · IEEE Intelligent Systems · doi:10.1109/mis.2025.3564330 · Cited by 18
“A common drawback of research proposing XAI methods is a lack of clarity on the use of quantitative evaluations [33].”
InfluentialInterpreting vision and language generative models with semantic visual priors
Cafagna, M., Rojas-Barahona, L. M., van Deemter, K., & Albert Gatt, A. (2023) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2023.1220476 · Cited by 10
Chang, C. H., Cook‐Patton, S. C., Erbaugh, J. T., Lu, L., Masuda, Y. J., Molnár, I. D., Papp, D., & Robinson, B. E. (2025) · Conservation Biology · doi:10.1111/cobi.14464 · Cited by 13
“Although XAI enhances transparency, curbs ethical risks, and accelerates discovery, rigorous validation across diverse data, tasks, and models is still crucial (Nauta et al., 2023).”
Design Principles and Guidelines for LLM Observability: Insights from Developers
Chen, X., Li, Y., & Wang, X. (2025) · Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706599.3719914 · Cited by 7
Explaining transformer-based next activity prediction by using attention scores
Käppel, M., Ackermann, L., Jablonski, S., & Härtl, S. (2025) · Process Science · doi:10.1007/s44311-025-00018-4 · Cited by 8
“This emphasizes the difficulty to distinguish between correct explanations for underperforming models from incorrect explanations for capable models (Nauta et al. 2023).”
InfluentialExplainable Graph Neural Networks in Chemistry: Combining Attribution and Uncertainty Quantification
Komissarov, L., Manevski, N., Zbinden, K. G., & Sach-Peltason, L. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01003 · Cited by 11
Klotz, J., Burgert, T., & Demir, B. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3624789 · Cited by 12
“This reliance on qualitative assessment raises concerns, as studies in the CV community have shown that qualitative assessment is insufficient for the robust verification of explanation methods [21], [22].”
Multimodal artificial intelligence for enhanced skin cancer diagnosis and prognosis
Karnwal, A., Selvaraj, M., Kumar, G., Kumar, A., Al-Tawaha, A. R., Aqueel-Ur-Rehman, & Nesterova, N. (2026) · Discover Oncology · doi:10.1007/s12672-026-04532-0 · Cited by 10
“Another study suggests combining meta-learning with unsupervised learning to improve cancer detection by enhancing the feature representations of meta-learning [30, 65].”
Explainability in vis-NIR and XRF-based modeling for soil fertility analysis: A comprehensive review
Ribeiro, J. V., Barbon, S., dos Santos, F. R., & Melquíades, F. L. (2026) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2026.118776 · Cited by 7
Qureshi, M. A., Noor, A. A., Manzoor, A., Mazhar Qureshi, M. D., Younus, A., & Rashwan, W. (2026) · PLOS One · doi:10.1371/journal.pone.0351473 · Cited by 7
An Empirical Analysis of User Preferences Regarding XAI Metrics
Darias, J. M., Bayrak, B., Caro-Martínez, M., Díaz-Agudo, B., & Recio-García, J. A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-63646-2_7 · Cited by 9
ConvNext as a Basis for Interpretability in Coffee Leaf Rust Classification
Chavarro, A., Renza, D., & Moya-Albor, E. (2024) · Mathematics · doi:10.3390/math12172668 · Cited by 12
Sanity checks for patch visualisation in prototype-based image classification
Xu-Darme, R., Quenot, G. M., Chihani, Z., & Rousset, M.-C. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00377 · Cited by 9
“During the last decade, the field of Explainable AI (XAI) has gained wide-spread recognition among the scientific community [6, 16].”
BackgroundEvalAttAI: A Holistic Approach to Evaluating Attribution Maps in Robust and Non-Robust Models
Nielsen, I. E., Ramachandran, R. P., Bouaynaya, N. C., Fathallah‐Shaykh, H. M., & Rasool, G. (2023) · IEEE Access · doi:10.1109/access.2023.3300242 · Cited by 16
“The first instinct is to visually examine an explainability map to see whether the attribution makes sense to a human observer [7], [22].”
BackgroundMethodLearning to generate and evaluate fact-checking explanations with transformers
Feher, D., Khered, A., Zhang, H., Batista-Navarro, R., & Schlegel, V. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109492 · Cited by 15
Karampasi, A. S., Grammatikis, P. I. R., Pawlicki, M., Choraś, R. S., de Pozuelo, R. M., Sarigiannidis, P. G., Puchalski, D., Pawlicka, A., Kozik, R., & Choraś, M. (2024) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw65004.2024.00041 · Cited by 9
“With this pressing necessity, xAI is now an intense area of research, with numerous emerging approaches [24].”
Improving skin lesion classification through saliency-guided loss functions
Dakhli, R., & Barhoumi, W. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110299 · Cited by 6
Evaluating Model Explanations without Ground Truth
Rawal, K., Fu, Z., Delaney, E. D., & Russell, C. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732219 · Cited by 15
VirtualXAI: A User-Centric Framework for Explainability Assessment Leveraging GPT-Generated Personas
Makridis, G., Koukos, V., Fatouros, G., Kotios, D., Separdani, M. M., Kyriazis, D., & Soldatos, J. K. (2025) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss-iot65416.2025.00156 · Cited by 8
“The approach is based on the XAI evaluation strategy presented in [13] and further enhanced with qualitative assessment levergaing LLM generated virtual personal based on an anthol-ogy of backstories and insights from three surveys [2] [32] [33].”
Cortiñas-Lorenzo, K., Cai, W., & Doherty, G. J. (2025) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3769678 · Cited by 14
Schäfer, U., Sipos, L., & Müller-Birn, C. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757451 · Cited by 13
Explainable Automated Anomaly Recognition in Failure Analysis: is Deep Learning Doing it Correctly?
Arrighi, L., Barbon, S., Pellegrino, F. A., Simonato, M., & Zullich, M. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44067-0_22 · Cited by 7
Navigating the Ethical Landscape: Considerations in Implementing AI-ML Systems in Human Resources
Basnet, S. (2024) · International Journal of Research Publication and Reviews · doi:10.55248/gengpi.5.0324.0755 · Cited by 14
“Notably, scholars such as Nauta et al. (2022) and Budhwar et al. (2022) have delved into topics ranging from the social impact of AI and robotics to the challenges and opportunities in international HRM, shedding light on the multifaceted aspects of AI-enabled HRM practices.”
BackgroundCross-Modality Image Interpretation via Concept Decomposition Vector of Visual-Language Models
Fang, Z., Yuan, Z., Li, Z., Chen, J., Kuang, K., Yao, Y., & Wu, F. Q. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3403167 · Cited by 9
Gokhale, G., Claessens, B., & Develder, C. (2024) · ACM International Conference on Future Energy Systems (e-Energy) · doi:10.1145/3632775.3663310 · Cited by 7
Attention Please: What Transformer Models Really Learn for Process Prediction
Käppel, M., Ackermann, L., Jablonski, S., & Härtl, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70396-6_12 · Cited by 10
PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans
Santi, L. A. D., Schlötterer, J., Scheschenja, M., Wessendorf, J., Nauta, M., Positano, V., & Seifert, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-77610-6_7 · Cited by 10
Self-citationOpen and Extensible Benchmark for Explainable Artificial Intelligence Methods
Moiseev, I., Balabaeva, K., & Kovalchuk, S. V. (2025) · Algorithms · doi:10.3390/a18020085 · Cited by 8
ODExAI: A Comprehensive Object Detection Explainable AI Evaluation
Nguyen, L., Nguyen, T. T. H., & Cao, H. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02813-6_9 · Cited by 11
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.