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 301–400 of 592
Tang, S., Ren, Z., Zheng, L., & Wang, J. (2026) · Sensors · doi:10.3390/s26175379 · Cited by 2
“Consequently, explanation quality should be evaluated quantitatively in terms of fidelity, stability, robustness, localization, and physical consistency rather than relying solely on visual inspection [109].”
Quantification of Explainability in Black Box Models using Complexity Measures
Nneke, N., Lloyd, H., & Crockett, K. A. (2023) · International Conference on Innovations in Information Technology · doi:10.1109/iit59782.2023.10366490 · Cited by 2
“…of an explanation however they been criticised in the literature as anecdotal evidence “showing individual convincing examples that pass the first test of having face validity” [18], [19] where the evaluation is based on the “researchers intuition of what constitutes a good explanation” [20].”
BackgroundResultInfluentialA Novel Metric for Evaluating the Stability of XAI Explanations
Gawantka, F., Just, F., Savelyeva, M., Wappler, M., & Lässig, J. (2024) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj090113 · Cited by 6
Interpretability in Sentiment Analysis: A Self-Supervised Approach to Sentiment Cue Extraction
Sun, Y., He, S., Han, X., & Luo, Y. (2024) · Applied Sciences · doi:10.3390/app14072737 · Cited by 4
Explainability Engineering Challenges: Connecting Explainability Levels to Run-Time Explainability
Schwammberger, M., Mirandola, R., & Wenninghoff, N. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63803-9_11 · Cited by 7
Knof, H., Boerger, M., & Tcholtchev, N. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63803-9_9 · Cited by 5
Bias Detection and Correction Methods for Machine Learning Algorithms
Dimitrakopoulou, G., Kapsalis, N. C., & Kokkinis, G. (2024) · International Conference in Electronic Engineering & Information Technology (EEITE) · doi:10.1109/eeite61750.2024.10654404 · Cited by 7
“Model evaluation: This is the stage where the algorithms are evaluated for their performance, impact, and implications on the data, the users, or the society [19].”
Evaluating the Pros and Cons of Recommender Systems Explanations
Wardatzky, K. (2024) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3640457.3688011 · Cited by 2
CEERS: Counterfactual Evaluations of Explanations in Recommender Systems
Baklanov, M. (2024) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3640457.3688015 · Cited by 4
Schwammberger, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73741-1_19 · Cited by 5
“As it would be out of the scope of this visionary paper, we do not go into details on this, but instead refer to two review papers on explanation validation through user studies [14,20].”
Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation
Valois, P. H. V., de Souza, L. S., Shimomoto, E. K., & Fukui, K. (2025) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.48 · Cited by 12
Conversational XAI: Formalizing Its Basic Design Principles
Garofalo, M., Fantini, A., Pellungrini, R., Pilato, G., Villari, M., & Giannotti, F. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-74627-7_22 · Cited by 4
Kumar, V., Kumar, R. K., & Singh, S. K. (2025) · SN Computer Science · doi:10.1007/s42979-025-03775-y · Cited by 4
LXR: Learning to eXplain Recommendations
Gurevitch, L., Bogina, V., Barkan, O., Schein, Y., Elisha, Y., & Koenigstein, N. (2025) · ACM Transactions on Recommender Systems · doi:10.1145/3732292 · Cited by 9
Srisuchinnawong, A., & Manoonpong, P. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251336385 · Cited by 6
“To quantitatively assess interpretability, four XAI evaluation metrics were used, following Nauta et al. (2023): GOLLUM, which has a higher interpretability and performance (see Figure 8).”
Evaluating Explanation Quality in X-IDS Using Feature Alignment Metrics
Alquliti, M., Karafili, E., & Kang, B. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-00630-1_4 · Cited by 2
Explainable clustering: Methods, challenges, and future opportunities
Dewoprabowo, R., Stefanus, L. Y., & Saptawijaya, A. (2025) · Journal of Intelligent Systems · doi:10.1515/jisys-2024-0477 · Cited by 7
Comprehensive Evaluation of Prototype Neural Networks
Schlinge, P., Meinert, S., & Atzmueller, M. (2025) · Künstliche Intell. · doi:10.1007/s13218-025-00900-0 · Cited by 5
Social AI Agents Too Need to Explain Themselves
Basappa, R., Tekman, M., Lu, H., Faught, B., Kakar, S., & Goel, A. K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-63028-6_29 · Cited by 9
Revisiting FunnyBirds Evaluation Framework for Prototypical Parts Networks
Opłatek, S., Rymarczyk, D., & Zieliński, B. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63787-2_4 · Cited by 5
Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing Their Contributions
Padmanabhan, N., Gwilliam, M., Kumar, P., Maiya, S. R., Ehrlich, M., & Shrivastava, A. (2024) · 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/cvpr52733.2024.01042 · Cited by 7
“This is not completely unique to INRs – explainability and interpretability are still massive challenges for other areas in vision as well [1, 2, 18, 38].”
Geyer, P., Singh, M. M., & Chen, X. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4833100 · Cited by 2
SIDU-TXT: An XAI algorithm for NLP with a holistic assessment approachPreprint
Jahromi, M. N. S., Muddamsetty, S. M., Jarlner, A. S. S., Høgenhaug, A. H., Gammeltoft‐Hansen, T., & Moeslund, T. B. (2024) · SocArXiv (OSF Preprints) · doi:10.31235/osf.io/jemvk · Cited by 2
Towards A Global AI Auditing Framework: Assessment and Recommendations
(IPIE), I. P. O. T. I. E., Faveri, B., Johnson-León, M., Sylvester, P., Chun, W. H. K., Hannák, A., Mendoza, M., Broussard, M., Сергеевич, Е. Р., Nelson, A., et al. (2025) · doi:10.61452/zwed1485 · Cited by 6
Assessment of Explainable Anomaly Detection for Monitoring of Cold Rolling Process
Jakubowski, J., Stanisz, P., Bobek, S., & Nalepa, G. J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-63775-9_24 · Cited by 1
“A more robust approach involves applying metrics for quantitative comparison across different methods [24].”
InfluentialRheem, H., Lee, J., Lee, J. D., Szczerba, J. F., & Tsimhoni, O. (2025) · Journal of Cognitive Engineering and Decision Making · doi:10.1177/15553434251318477 · Cited by 2
“This is in line with Nauta et al. (2023), which identi fi ed quanti fi able attributes of good explanations from a literature review of XAI research.”
InfluentialOffenberg, R., Luca, A. D., Biessels, G. J., Barkhof, F., van der Flier, W. M., van Harten, A. C., van der Lelij, E. J., Pluim, J. P. W., & Kuijf, H. J. (2025) · NeuroImage Clinical · doi:10.1016/j.nicl.2025.103790 · Cited by 1
“No false negative ROIs were detected in group-level attribution maps.”
"Good" XAI Design: For What? In Which Ways?
Wang, L., Liu, Y., & Goel, A. K. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3720036 · Cited by 4
Addressing the Paradox of Using AI in Ethics and Compliance Through a Checklist-Based Solution
Viganò, E., Hauser, C., & Weichselbraun, A. (2025) · Integrated science · doi:10.1007/978-3-031-87023-1_13 · Cited by 1
Quantifying Explainability: Essential Guidelines for Evaluating XAI Methods
Djellikh, S., Youkana, I., Ammari, A., & Saouli, R. (2025) · International Symposium on iNnovative Informatics of Biskra (ISNIB) · doi:10.1109/isnib64820.2025.10983231 · Cited by 1
“Despite the significant progress in the field and the importance of evaluation, there is no gold standard evaluation strategy for XAI methods [3].”
Navigating the informativeness-compression trade-off in XAI
Oldenburg, N., & Søgaard, A. (2025) · AI and Ethics · doi:10.1007/s43681-025-00733-5 · Cited by 4
“…to measuring predictability include: (a) Preservation Check → Model as evaluator [82] (b) Predictive Performance → Model, compared to ground truth [82] (c) Human Forward Prediction → Human as the evaluator [83] (d) Reverse Turing Test → Human evaluator after training [43] Preservation checking…”
Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
Dhaini, M., Erdoğan, E., Feldhus, N., & Kasneci, G. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732192 · Cited by 9
On the role of explanations in machine learning prediction of nonalcoholic steatohepatitis
Babakov, N., Rezgova, E., Reiter, E., & Bugarín, A. (2025) · Progress in Artificial Intelligence · doi:10.1007/s13748-025-00387-8 · Cited by 2
Evaluation of Local Explainability Methods in Turkish Text Classification Tasks
Porsuk, O., Yıldırım, S., & Başar, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-92602-0_30 · Cited by 1
Sabir, B., Gao, Y., Abuadbba, A., & Babar, M. A. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3624268 · Cited by 8
“Particularly when applied to complex models such as BERT and RoBERTa, the computational overhead makes these techniques less feasible for real-time applications [25].”
HeteroX: An interpretable Dual-tier Heterogeneous Graph for sustainable investment decisions
Taghikhah, F. R., Hosseinpour, S., & Gao, J. (2025) · Computers & Industrial Engineering · doi:10.1016/j.cie.2025.111640 · Cited by 1
Explainable AI-Enabled Intrusion Detection Systems for Computer Networks
Manivannan, D. (2025) · IEEE International Conference on Cyber Security and Cloud Computing (CSCloud) · doi:10.1109/cscloud66326.2025.00053 · Cited by 1
“Nauta et al. [56] identified 12 key properties (Co-12) for assessing explanation quality, including correctness, completeness, consistency, and confidence.”
A Literature Review on Example-Based Explanations in Medical Image Analysis
Montenegro, H., & Cardoso, J. S. (2025) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-025-00227-3 · Cited by 1
Zanon, A. L., da Rocha, L. C. D., & Manzato, M. G. (2025) · ACM Transactions on Recommender Systems · doi:10.1145/3779420 · Cited by 2
DERI1000: A New Benchmark for Dataset Explainability Readiness
Pisarcik, A., Hudec, R., & Hlavata, R. (2025) · AI · doi:10.3390/ai6120320 · Cited by 1
“…systematic review “From Anecdotal Evidence to Quantitative Evaluation Meth-ods: A Systematic Review on Evaluating Explainable AI”, in the article [5], analyzes over 300 papers and identifies 12 conceptual properties (the “Co-12” framework) that explanations should ideally satisfy, such as…”
VCR: Interpretable and interactive debugging of object detection models with visual concepts
Xu, J., Dhanani, S., Ono, J. P., He, W., Ren, L., & Rong, K. (2025) · Information Systems · doi:10.1016/j.is.2025.102652 · Cited by 1
Chakraborty, T., Koelle, M., Schlötterer, J., Schlicker, N., Wirth, C., & Seifert, C. (2025) · Information Systems Frontiers · doi:10.1007/s10796-025-10671-6 · Cited by 1
“Due to prohibitive cost and effort, most XAI researchers resort to functionally-grounded evaluation and few conduct user studies [44].”
Self-citationInterpretable World Model Imaginations as Deep Reinforcement Learning Explanation
Wenninghoff, N., & Schwammberger, M. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08327-2_7 · Cited by 3
XAI In Fraud Detection: A Causal Perspective
van Veen, K., Ahmed, F., & van Keulen, M. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08330-2_15 · Cited by 1
ProtoMask: Segmentation-Guided Prototype Learning
Meinert, S., Schlinge, P., Strodthoff, N., & Atzmueller, M. (2025) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai66417.2025.00128 · Cited by 1
“General studies have demonstrated the complexity and diversity of quantative evaluation techniques employed in our context [35] [36].”
A visualization-driven decision support system for selecting feature attribution methods
Silva, P., Ortigossa, E. S., Turakhia, D. G., Silva, C., & Nonato, L. G. (2026) · Information Systems · doi:10.1016/j.is.2025.102661 · Cited by 2
Yoon, S., Shin, H., & Choi, J. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2602717 · Cited by 1
“However, these measures do not comprehensively assess epistemic aspects of explanation—such as perceived interpretability, transparency, or explanatory soundness—which are central to explainable AI (Rong et al., 2024; Nauta et al., 2023).”
Perspective Chapter: Validation and Quality Metrics of Machine Learning Explanations
García-Cuesta, E., & González, A. M. L. (2026) · IntechOpen eBooks · doi:10.5772/intechopen.1013468 · Cited by 1
Nápoles, G., Grau, I., & Salgueiro, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.132925 · Cited by 2
SPAX: A Shapley-Based Point Attribution eXplanation for Interpreting 3D Point Cloud Classification
Harinck, M. F., Sarwar, M. S., Ton, B., & Ahmed, F. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-15638-9_24 · Cited by 1
Taghikhah, F. R., Malik, A., Voinov, A. A., Govindan, K., & Tosarkani, B. M. (2026) · Energy Policy · doi:10.1016/j.enpol.2026.115141 · Cited by 1
Explainable AI for Renewable Energy Project Prefeasibility Analysis
Moses, S. S., & Thornburg, J. (2025) · Asia-Pacific Power and Energy Engineering Conference (APPEEC) · doi:10.1109/appeec66370.2025.11382138 · Cited by 1
“This metric builds on the concept of completeness being the ability to ”cover the whole truth” [12], [14] and is an adaptation of the foundational recall formula for information retrieval developed by Manning et. al [11].”
Shehada, D. J. M., Tawfik, H., Bouridane, A., & Hussain, A. (2026) · Computers · doi:10.3390/computers15030139 · Cited by 1
Zhang, Y., Wärnberg, H., Huehnerbein, R. D., Bhattacharya, N., Brorsson, E., Darnell, A., & Buelow, F. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10697-4 · Cited by 2
When Splits Matter: Interpreting Disaster Tweet Classification Models
Livers, J., Johnson, N., Spurlock, K., & Nasraoui, O. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00363 · Cited by 1
“Several recent studies have evaluated XAI metrics and explanation quality using quantitative benchmarks and human validation, emphasizing the need for reliable evaluation frameworks [5], [6].”
Yadav, S., Kaushik, A., & McDaid, K. (2026) · Applied AI Letters · doi:10.1002/ail2.70028 · Cited by 1
Aly, S., Young, H., Rimmer, J. H., & Mehta, T. S. (2026) · Healthcare · doi:10.3390/healthcare14060781 · Cited by 1
SH-BRB: A semantically-grounded and explainable AI framework for dynamic mental health assessment
Chi, Y., Li, S., Wang, Y., Huang, H., Wang, J., Ji, K., Li, X., & Zhao, Y. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00677-8 · Cited by 1
“A multifaceted evaluation system was adopted to assess clinical utility: Weighted F1-Score: The primary metric for overall multi-class performance (Nauta et al. 2023).”
Malik, M. H., Wan, Z., & Ding, D.-W. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110228 · Cited by 4
Four Aspirations for Evaluating AI-Infused Technologies: A Narrative Review
Morey, D. A., Jalaeian, M., Reynolds, M. E., McGeorge, N., Oldham, H. K., & Rayo, M. F. (2026) · Journal of Cognitive Engineering and Decision Making · doi:10.1177/15553434261443032 · Cited by 1
“For example, as few as 5% of explainable AI evaluations involved intended end users (Nauta et al., 2023).”
InfluentialNaib, P., Park, J., Abedin, P., King, C., & Gurupur, V. P. (2026) · Information · doi:10.3390/info17050438 · Cited by 1
Explain it for Safety: Explanations for Risk Mitigation
Schwammberger, M., Rakow, A., Putze, L., & Bairy, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-16855-9_16 · Cited by 1
Evaluating Explainability: Metrics, Benchmarks, and Human-Centered Evaluation Methods
Yousefi, N., & Zamanifar, A. (2026) · Springer eBooks · doi:10.1007/978-3-032-15088-2_10 · Cited by 1
A Systematic Review of Explainable Convolutional Neural Networks for Image Classification
Hasić, V., & Krivić, S. (2026) · Expert Systems · doi:10.1111/exsy.70279 · Cited by 2
Idaji, M. J., Hense, J., Neuhauser, T., Krause, A., Luo, Y., Eberle, O., Schnake, T., Ciernik, L., Jafari, F. R., Vahidimajd, R., et al. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104148 · Cited by 8
“Third, different explanation meth-ods can also yield substantially different heatmaps [60, 61, 62].”
A Review of Taxonomies of Explainable AI (XAI) Evaluation
Speith, T. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3806537 · Cited by 3
“[1, 3–5, 7, 12, 14, 15, 21, 23, 26, 27, 53, 60, 70, 74, 90, 98, 101, 108, 110, 118, 120, 127, 128, 130, 135, 139, 149, 155, 161, 164, 167, 177, 180, 193, 197, 199, 201 [25, 66, 112, 114, 122, 131, 133, 191, 196] More Other 24 [6, 9, 35, 39, 40, 44, 54, 55, 59, 63, 76, 83, 91–93, 103, 123, 129,…”
InfluentialWhewell, J., Peters, R., & Kulon, J. (2026) · Technologies · doi:10.3390/technologies14070391 · Cited by 5
Seeing the trade-offs: Evaluating visualizations for multi-criteria comparison of set alternatives
Chakhchoukh, M., Bezerianos, A., & Boukhelifa, N. (2026) · Information Visualization · doi:10.1177/14738716261457001 · Cited by 1
AI Transparency: Governance Compliance or Stakeholder Requirements?
Bano, M., & Zowghi, D. (2026) · IEEE International Requirements Engineering Conference (RE) · doi:10.1109/re68928.2026.00021 · Cited by 1
“Recent systematic reviews highlight definitional divergence and conceptual fragmentation across the field [31]–[33].”
Leveraging Mutation Analysis for LLM-Based Repair of Quantum Programs
Yoshida, C., Ishimoto, Y., Nourry, O., Kondo, M., Matsushita, M., Kamei, Y., & Higo, Y. (2026) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner67736.2026.00019 · Cited by 3
“The quality of explanations is evaluated using three criteria proposed in previous work [31], [32]: • Correctness: Is the explanation accurate with respect to the ground-truth fixed code?”
Explainable AI for subsurface carbon capture, utilization, and storage systems: A review
Davoodi, S., Moosazadeh, M., Imasuly, G. B., Al-Shargabi, M., Wood, D. A., & Burnaev, E. V. (2026) · Fuel · doi:10.1016/j.fuel.2026.140588 · Cited by 1
Baskerville, C., Willaime, J. M. Y., Prakash, V., Ali, T., Bhuva, S., Ellul, G., Frood, R. T., Kamat, S. V., Maitra, S., Rosewarne, D., et al. (2026) · La radiologia medica · doi:10.1007/s11547-026-02226-9 · Cited by 2
Toward Human-Centered Explanations for Agentic AI: Taxonomy, Mapping, and Evaluation
Hou, X., Mualla, Y., & Dridi, M. (2026) · International Conference on Human Centric Artificial Intelligence (ICHCAI) · doi:10.1109/ichcai70183.2026.11607607 · Cited by 2
“This tension is especially pronounced in agentic AI, where decisions depend on long sequences of intermediate steps and external interactions [33], [52].”
InfluentialRezaei, Z., Amini, M. A., & Banad, Y. M. (2026) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2026.111859 · Cited by 1
Geng, Z., Wu, D., Zhao, X., Hu, C., Qiu, P., Fu, C., & Liu, J. (2026) · Academia Catalysis · doi:10.20935/acadcatal8457 · Cited by 1
Lavecchia, A. (2026) · Medicinal Research Reviews · doi:10.1002/med.70098 · Cited by 6
User Mental Models as a Lens for Evaluating Explainable-AI System Outputs
Ardito, C. A., Bonis, M. L. N. D., Noia, T. D., Sciascio, E. D., Fasano, G., & Lombardi, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-22934-2_14 · Cited by 1
Quantitative Evaluation of Video Explainability Methods via Anomaly Localization
Zhang, X., Joukovsky, B., & Deligiannis, N. (2023) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco58844.2023.10290127 · Cited by 1
“For instance the co-12 properties [23] were proposed to comprehensively evaluate explainability methods on different aspects.”
BackgroundAlign MacridVAE: Multimodal Alignment for Disentangled Recommendations
Avas, I., Allein, L., Laenen, K., & Moens, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56027-9_5 · Cited by 1
Learning Performance Maximizing Ensembles with Explainability Guarantees
Pisztora, V., & Li, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i13.29378 · Cited by 1
Towards a Framework for Interdisciplinary Studies in Explainable Artificial Intelligence
Ziethmann, P., Stieler, F., Pfrommer, R., Schlögl-Flierl, K., & Bauer, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-60606-9_18 · Cited by 1
“Typically, the understandability, relevance, and accuracy of the explanation are evaluated [32], which, according to the approach of Doshi-Velez and Kim, can be determined concerning specific tasks and either through human or non-human input [12].”
Time for an Explanation: A Mini-Review of Explainable Physio-Behavioural Time-Series Classification
Schneider, J., Cheruvalath, S. S., & Hassan, T. (2024) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3675094.3679001 · Cited by 1
Bousnina, N., Ascenso, J., Correia, P. L., & Pereira, F. M. B. (2024) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-024-00645-0 · Cited by 1
“…number of explainability tools available, a pressing requirement emerges for explainability performance assessment methodologies, to evaluate the power and usefulness of the explanations provided and determine whether and to what extent the offered explanations achieve the targeted objectives [13].”
BackgroundSlide to Explore 'What If': An Analysis of Explainable Interfaces
Meyer, L. S., & Zhu, J. (2024) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3677045.3685416 · Cited by 5
Integrating XAI into Safe AI Development and AI Certification Processes: An Expert-Based Analysis
Frész, B., Göbels, V. P., Omri, S., Brajovic, D., Aichele, A., Kutz, J., Neuhüttler, J., & Huber, M. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30849-8_13 · Cited by 11
“Some authors also call for uncertainty (or “confidence”) estimates of explanations themselves to show whether a generated explanation should be trusted (Nauta et al. 2023; Fresz et al. 2024).”
BackgroundZhang, L. (2024) · International Journal of Knowledge Management · doi:10.4018/ijkm.356634 · Cited by 1
Explaining Image Classifiers with Visual Debates
Kori, A., Glocker, B., & Toni, F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-78980-9_13 · Cited by 6
Building Intrinsically Interpretable Deep Neural Networks: A Survey
Zhang, W., Jiao, L., & Pan, Q. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10865081 · Cited by 3
“Nauta et al [5] proposed 12 conceptual attributes, such as Compactness, to analyze the explanation in multiple ways, and use these attributes to systematically evaluate interpretable methods in recent years to assess the quality of the interpretations.”
Insights into Quantitative Evaluation Techniques for AI Explainability
Gomes, H. S., Ferreira, J., & Rodrigues, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-82073-1_29 · Cited by 1
Barile, R., d’Amato, C., & Fanizzi, N. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714667 · Cited by 4
Kabir, S., Hossain, M. S., & Andersson, K. (2025) · Algorithms · doi:10.3390/a18060305 · Cited by 4
Hidden Conflicts in Neural Networks and their Implications for Explainability
Dejl, A., Zhang, D., Ayoobi, H., Williams, M., & Toni, F. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732100 · Cited by 6
The Double-Edged Sword of Behavioral Responses in Strategic Classification: Theory and User Studies
Ebrahimi, R., Vaccaro, K., & Naghizadeh, P. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732056 · Cited by 11
Mao, R. (2025) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit65432.2025.11035726 · Cited by 1
“Applying deep learning to the quantitative evaluation of embroidery can not only improve data processing efficiency and accuracy but also automatically identify key factors that influence the artistic value of embroidery through the analysis of a large number of embroidery works[1].”
Mathematical Foundation of Interpretable Equivariant Surrogate Models
Colombini, J. J., Bonchi, F., Giannini, F., Giannotti, F., Pellungrini, R., & Frosini, P. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08324-1_13 · Cited by 3
Ronckers, M., Conijn, R., & Snijders, C. C. P. (2024) · doi:10.17504/protocols.io.n92ld89e8v5b/v1
Wang, H., Aligon, J., May, J., Doumard, E., Labroche, N., Delpierre, C., Soulé-Dupuy, C., Casteilla, L., Planat‐Benard, V., & Monsarrat, P. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.04.06.647498 · Cited by 1
“…the functionally-grounded evaluations are less cost-intensive, but concentrate on objective functionality, such as correctness (faithfulness of the explanation with the predictive model), consistency (identical inputs have identical explanations), and compactness (size of the explanation) [12].”
Procedure to Evaluate Artificial Intelligence (AI) Output for Educational and Clinical Tasks
Gilbertson, L., Busch, C. M., Spike, J., DeMoss, K., & Thompson, J. (2026) · Teaching and Learning in Communication Sciences & Disorders · doi:10.61403/2689-6443.1398
Comparing model-agnostic and model-specific XAI methods in Natural Language Processing
Sandu, M. G., & Trăușan-Matu, Ș. (2022) · RoCHI - International Conference on Human-Computer Interaction (RoCHI) · doi:10.37789/rochi.2022.1.1.19 · Cited by 1
“A very thorough review on the evaluation metrics for XAI was performed on approximately 600 papers, and concluded that there are 12 quality properties that should be further studied [8].”
BackgroundMethodInfluentialL'explicabilité au service de l'extraction de connaissances : application à des données médicalesPreprint
Cugny, R., Doumard, E., Escriva, E., & Wang, H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.02653 · Cited by 2
“, 2016] et SHAP [Lundberg and Lee, 2017] sont celles qui suscitent le plus de propositions scientifiques et sont les plus populaires, autant dans la recherche que l’industrie [Nauta et al., 2022].”
Background
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.