Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics
Open accessThe DOI matches its Crossref record; 88 of the 88 references it cites were found in a registry or an index.
Abstract
The most successful Machine Learning (ML) systems remain complex black boxes to end-users, and even experts are often unable to understand the rationale behind their decisions. The lack of transparency of such systems can have severe consequences or poor uses of limited valuable resources in medical diagnosis, financial decision-making, and in other high-stake domains. Therefore, the issue of ML explanation has experienced a surge in interest from the research community to application domains. While numerous explanation methods have been explored, there is a need for evaluations to quantify the quality of explanation methods to determine whether and to what extent the offered explainability achieves the defined objective, and compare available explanation methods and suggest the best explanation from the comparison for a specific task. This survey paper presents a comprehensive overview of methods proposed in the current literature for the evaluation of ML explanations. We identify properties of explainability from the review of definitions of explainability. The identified properties of explainability are used as objectives that evaluation metrics should achieve. The survey found that the quantitative metrics for both model-based and example-based explanations are primarily used to evaluate the parsimony/simplicity of interpretability, while the quantitative metrics for attribution-based explanations are primarily used to evaluate the soundness of fidelity of explainability. The survey also demonstrated that subjective measures, such as trust and confidence, have been embraced as the focal point for the human-centered evaluation of explainable systems. The paper concludes that the evaluation of ML explanations is a multidisciplinary research topic. It is also not possible to define an implementation of evaluation metrics, which can be applied to all explanation methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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 cited source says what the claim attributes to it.
In the citing paper
“They found that some properties (clarity, broadness, and completeness) are still in shortage of appropriate metrics, and so is the class of explanations that are example-based.”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [141]
In the citing paper
“It is not possible to come up with quantitative metrics that are applicable for all interpretability methods [169].”
From Transparency of deep neural networks for medical image analysis: A review of interpretability methods (2022) · cites this paper as [169]
In the citing paper
“They conclude their survey by stating that”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [141]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 2×
“One way to objectively evaluate explanations is to verify whether the explanation mechanism satisfies (or does not satisfy) certain axioms, or properties [34].”
Background"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
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 1×
“[39] explained an ensemble of models, such as neural networks with a single model effectively.”
BackgroundCausality: Models, Reasoning, and Inference
Pearl, J. (2009) · doi:10.1017/cbo9780511803161 · Cited by 11,653
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“Explanation is also a domain-specific note, and there cannot be an all-purpose explanation [22], and different types of explanations might be useful.”
BackgroundPeeking 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 2×
“The machine learning explainability has been reviewed thoroughly in recent years [10,14,17,23,28,31,32].”
BackgroundLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087 · cited 4×
“…Main effect complexity [46] Level of (dis)agreement [82] Attribution-based explanations Monotonicity [80] Non-sensitivity [80,83], Sensitivity [84,85] Effective complexity [80] Remove and retrain [86] Recall of important features [33] Implementation invariance [85] Selectivity [87] Continuity…”
BackgroundInfluentialTowards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121 · cited 4×
“The advantages of application-grounded and human-grounded evaluations are that they can provide direct and strong evidence of success of explanations [9].”
BackgroundMethodInfluential
Research works printed but not linked: 5
- Zhou, J., and Chen, F. (2018). Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent, Springer.
- Lage, I., and Doshi-Velez, F. (2020, January 17). Human-in-the-Loop Learning of Interpretable and Intuitive Representations. Proceedings of the ICML Workshop on Human Interpretability in Machine Learning, Vienna, Austria.
- Becker, B., Kohavi, R., and Sommerfield, D. (2001). Visualizing the Simple Bayesian Classifier. Information Visualization in Data Mining and Knowledge Discovery, Morgan Kaufmann Publishers Inc.
- Poursabzi-Sangdeh, F., Goldstein, D.G., Hofman, J.M., Vaughan, J.W., and Wallach, H. (2019). Manipulating and Measuring Model Interpretability. arXiv.
- Yang, M., and Kim, B. (2019). Benchmarking Attribution Methods with Relative Feature Importance. arXiv, 1907.
Cited by
Items 601–676 of 676
Somani, A., & Prasad, D. K. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00083
Gali, V. K. (2023) · International Journal of Artificial Intelligence Data Science and Machine Learning · doi:10.63282/3050-9262.ijaidsml-v4i1p114
Модель виявлення шахрайських доменних імен
Олександрівна, Ш. В. (2024) · eKNUTSHIR
Shank, D. B., Canfield, C., & Subramanian, H. V. (2024) · OSF Preprints (OSF Preprints)
MASE: Interpretable NLP Models via Model-Agnostic Saliency Estimation
Yang, Z., Luo, S., Zhu, J., & Jin, F. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402020
“Motivated by previous work [46], [47], we measure the performance of the proposed method by faithfulness.”
Assessment of ChatGPT-4.0 versus ChatGPT-Mini in Generating Guideline-Based Hypertension Content
Ataídes, R. J. C., Campos, M. A. G., de Souza, J. V. P., Rocha, R. C., Lacalle, A. A., Vieira, C. B., Artioli, T., Medeiros, T. C., Filho, E. M. D. S., Gismondi, R. A., et al. (2026) · Arquivos Brasileiros de Cardiologia · doi:10.36660/abc.20250498 · Cited by 1
Ilyas, M., Okafor, K., Sohrab, F., & Abrahamsson, P. (2026) · IEEE Access · doi:10.1109/access.2026.3676942
Understanding and the Black Box Problem in Artificial Intelligence
Crook, B. (2025) · EPub Bayreuth (University of Bayreuth) · doi:10.15495/epub_ubt_00008992
Designing and evaluating explanation user interfaces for complex Machine Learning systems
Bove, C. (2023) · theses.fr (ABES) · doi:10.70675/87604ec1z34bfz4c27za5dezfa41299abde8
Generality and explainability in recommender systems
Zhong, J. (2023) · theses.fr (ABES) · doi:10.70675/de5345e1z9ed3z4064zaaf4zc45a557c0632 · Cited by 2
Towards Reliable Post Hoc Explanations for Machine Learning on Tabular Data and their Applications
Ayad, C. W. (2024) · theses.fr (ABES) · doi:10.70675/9e4de1adz26e2z41d1z9451z80421221b06d
Argument-based natural language explanation generation and assessment in healthcare
Molinet, B. (2024) · theses.fr (ABES) · doi:10.70675/dcb29a70z3429z4ab0zb096z98206dd11eab · Cited by 1
Srivastava, A., & Maity, R. (2026) · Springer eBooks · doi:10.1007/978-3-032-17991-3_16 · Cited by 1
Interpretable and Causal Analysis for Multivariate Time Series
Dhaou, A. (2024) · theses.fr (ABES) · doi:10.70675/5d446b35z9b19z42afz85e4zf645a7788981 · Cited by 2
Explaining reinforcement learning
Saulières, L. (2024) · theses.fr (ABES) · doi:10.70675/ef57c459z3e5bz437czbc31zec8bfff34d87 · Cited by 1
Intentional policy graphs: A pipeline for explaining agent behavior through intentions
Giménez-Ábalos, V., Álvarez-Napagao, S., Tormos, A., Montese, S., Ulises Cortés, A., & Vázquez-Salceda, J. (2026) · Patterns · doi:10.1016/j.patter.2026.101513
On the Importance and Evaluation of Narrativity in Natural Language AI ExplanationsPreprint
Cedro, M., & Martens, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.18311 · Cited by 1
“Assessing the quality of generated natural language explanations is not trivial [42, 25].”
Classifying Digital Wallet Apps by Transaction Intensity: A Machine Learning Approach
Kumar, T. K. S., VijayaKumar, R., Annapoorna, M. S., & Singha, S. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5032-5.ch009
Deep Performance Analysis in the Interpretability and Explicability of Artificial Intelligence (XAI)
Aitouhanni, I., Berqia, A., Fares, H., Bouijij, H., Mouniane, Y., & Vibhute, A. D. (2026) · Wiley eBooks · doi:10.1002/9781394305612.ch5
Collaborative and Co-creative Communication with AI
Geroimenko, V. (2026) · Human-computer interaction series · doi:10.1007/978-3-032-21689-2_6 · Cited by 1
Evaluating the Quality of Generative AI Explanations: A Mathematics Perspective
Stulianec, A., & Fortis, A. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-22798-0_12
Sustainability and corporate valuation: A machine learning approach
Carvajal, V., Kristjanpoller, W., & Minutolo, M. C. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115518
Graph-prompted explainable fake news detection with multimodal large language models
Zhou, Y., Li, P., Han, K., & Cheng, S. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104883 · Cited by 1
A hybrid explainable intrusion detection system for fair and trustworthy cybersecurity
Chinu, & Urvashi (2026) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2026.111218
Sun, X., Xue, H., Sharma, D. P., Xue, L., Lin, X., & Xiong, P. (2026) · Journal of Information and Intelligence · doi:10.1016/j.jiixd.2026.05.005
Chinnameda, S. P. (2025) · TRAP@NCI (National College of Ireland)
Capiola, A., Jessup, S. A., Alarcon, G. M., Meyers, S. K., Johnson, D., & Ryan, T. J. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2676768
Babeker, M. I. A., Omer, A. A. A., Raza, S. M., Xiang, H., & Li, S. (2026) · Journal of Food Measurement & Characterization · doi:10.1007/s11694-026-04476-7
“In addition, the model remains directly interpretable, allowing explicit identifica - tion of the morphological traits driving classification deci - sions an aspect that is often less transparent in deep learning systems [12, 15 ].”
EXCODER: EXplainable Classification Of DiscretE Time Series Representations
Hahn, Y., Königsfeld, A., Tercan, H., & Meisen, T. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1300-9_27 · Cited by 1
Kulkarni, M., Joshi, D., & Patel, S. (2026) · Journal of Pharmaceutical Innovation · doi:10.1007/s12247-026-10795-5
“Keywords Artificial intelligence · Pre-screening tool · Drug-excipient compatibility · Drug profiling · AI-based predictive tool the field [ 17, 18].”
Dual-circle: a new way of assessing temporomandibular joint disc position at coronal MRI
Zhang, W., Sun, J., Liu, Z., Li, Y. X., Guo, J., & Yang, C. (2026) · Dentomaxillofacial Radiology · doi:10.1093/dmfr/twag020
Tulkittavuusohjattu regularisointi asemakohtaisessa sääennustamisessa
von Hertzen, A. (2026) · Aaltodoc (Aalto University)
Kuse, K. A., Agbangba, C. E., & Kakaï, R. G. (2026) · Discover Soil. · doi:10.1007/s44378-026-00256-3
The Impact of Explanation Characteristics on the Effects of Recommender Systems Explanations
Wardatzky, K., Inel, O., Rossetto, L., Kyriakou, A., & Bernstein, A. (2026) · ACM Computing Surveys · doi:10.1145/3856207
Introduction to Machine Learning for chemical engineers
Akbar, N. S., Batool, G., Farooq, M., & Jradi, L. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-33943-1.00011-3
Albreem, S. N. S., Zain, J. M., & Jumaat, A. K. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-8368-3_12
221Chapter 9 Neuro-Symbolic Reinforcement Learning with Advantage Actor-Critic
Bhat, S., Ramasamy, G., Sivalingam, E., & Ramachandran, S. (2026) · De Gruyter eBooks · doi:10.1515/9783111633909-009
Rebalancing the algorithm: pathways for mitigating bias in predictive policing
Nautiyal, L., Malik, P., Mittal, V., & Zieni, B. (2026) · Service Oriented Computing and Applications · doi:10.1007/s11761-026-00501-1
Trust by design: Human factors and trust calibration in ML-based educational systems
Anthis, Z., & Kyriakidou-Zacharoudiou, A. (2026) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2026.103893
Balancing usefulness and naturalness: an LLM-based curation pipeline for code review comments
Sghaier, O. B., Weyssow, M., & Sahraoui, H. A. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10928-x
“We first compute unigram, bigram, and trigram diversity , defined as the ratio of distinct n -grams over the total number of n -grams in the dataset: This captures the breadth of vocabulary at the token level as well as the richness of multiword expressions (Zhou et al., 2021; Li et al., 2015).”
Budiarti, R. P. N. (2026) · Journal of Intelligent Decision Making and Information Science · doi:10.59543/jidmis.v3.993
“The performance of each algorithm was evaluated using four common metrics in classification tasks: accuracy, precision, recall, and F1-score [46], [47], [48], [49], [50], [51].”
Machine Learning-Driven Advances in Hydrogen Embrittlement of Steels: A Comprehensive Review
Talkhan, A. G., Eljack, F., & Karagöz, S. (2026) · Hydrogen · doi:10.3390/hydrogen7030125
Malik, T. S. (2026) · Global Academic Journal of Economics and Business · doi:10.36348/gajeb.2026.v08i04.047
Explainable AI for Trustworthy 6G Edge-Cloud Smart Cities: A Systematic Review
Abbas, Q., & Almakki, R. S. (2026) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2026.0170850
“While relatively inexpensive and widely applicable, results from feature-attribution methods may be unstable and are often misinterpreted as causal [22 – 25, 44, 49].”
From Prediction to Physical Meaning in Materials AI
Li, M., & Lin, P. (2026) · ACS Materials Au · doi:10.1021/acsmaterialsau.6c00170
Skaik, R., Alan, A., Kutlu, M., Almarshoud, M., & Own, H. S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7411187
Varma, D., Parmar, R., Bhat, S., & Dutta, P. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108807
Pereira, L., & Martins, B. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/q969725355
Sudjarid, W., & Jarupunphol, P. (2026) · Journal of Data Science and Intelligent Systems · doi:10.47852/bonviewjdsis620210062
“However, final interpretation should remain human-reviewed because short project texts may not fully capture project objectives, implementation design, or real-world impact [9 – 11, 13, 15].”
Differentiability of classifier decision surface for evaluating faithfulness in local explanations
Soroush, K., Nõmm, S., & Belikov, J. (2026) · IFAC Journal of Systems and Control · doi:10.1016/j.ifacsc.2026.100445
Explainable machine learning for leukaemia diagnosis: enhancing interpretability and trust
Owida, H. A., Hassan, M. R., Turab, N. M., & Abuowaida, S. F. A. (2026) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v43.i3.pp817-823
“Proper data preprocessing, feature extraction, and selection are crucial steps to ensure that the model can learn meaningful patterns from the data [33].”
Benchmarking Explainability Methods for SME Credit Risk Models in Emerging Markets
Chowdhury, S., & Das, A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32729-1_33
TRANSPARENCY AND INTERPRETABILITY IN ARTIFICIAL INTELLIGENCE SYSTEMSPreprint
Bashabsheh, D. N. M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7468539
Kim, D., Park, J., Kang, M.-S., & Jung, H.-W. (2026) · Journal of Medical Sciences and Interdisciplinary Research · doi:10.51847/k7zkmq6ev7
Saleh, M., Abdelaziz, M. I., & Abdou, M. A. (2026) · International Journal of Computers and Applications · doi:10.1080/1206212x.2026.2731403
Shanthi, S., Sudha, M., Kamatchi, C., Saranya, S., & Vidhyalakshmi, A. M. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45697-8.00017-7
Adapting Vision-Language Models for Human-Readable XAI in Industrial Object DetectionPreprint
Sardari, S., Fernandes, F., Yelvande, S., Araya-Martinez, J. M., & Roitberg, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.31690
“Zhou et al. propose metrics bridging LLM and XAI evaluation [12], which we adapt with expert input for industrial use cases.”
InfluentialSattar, K. A., Ishak, I., Affendy, L. S., Rum, S. N. M., & Rahman, S. M. (2026) · Heliyon · doi:10.1016/j.heliyon.2026.e45513
DFO-CAM: Dual-Flow Optimization Toward Faithful Visual Explanations
Mi, J., Shi, S., & Li, W. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3737050
“In prior studies on explainability, several works [46], [48] have attributed issues similar to those observed in Figures 1 and 6 to the output completeness [51], [52] or correctness [47], [50] of explanation methods.”
XAI Evaluation Cards: A Practical Method for Designing Human-Centred XAI EvaluationsPreprint
Kacafírková, K. S., Donoso-Guzmán, I., Parra, D., Verbert, K., & Jacobs, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.02011
“Although subjective measures have sometimes been criticised for their dependence on users’ perceptions and context [47], relying exclusively on objective measures provides only a partial account of explanation quality.”
Dugăeșescu, A., & Florea, A. M. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8100315
Al-Ghraibah, A. M., Arabiat, A. M., & Altayeb, M. (2026) · International Journal of Biomedical Imaging · doi:10.1155/ijbi/8859105
“On the other hand, recall (sensitivity) refers to the percentage of pertinent facts that were successfully recovered; it is given by Equation (9) ([32]; [33]; [34]).”
To Think or Not to Think: Evaluating LLM Reasoning and Agents in Vulnerability Detection
Tan, H. B., Widyasari, R., Astekin, M., Göknil, A., Sözer, H., Tun, Y. N., Husom, E. J., Shar, L. K., & Jiang, L. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3837521
“Each dimension is rated on a five-point Likert scale [12, 49, 55, 56, 67].”
Evaluation of Plausibility and Robustness in Counterfactual Explanations
Benavides, G. M., Bequer, E. D. S., Lorenzo, M. M. G., & Bello, R. (2026) · Studies in computational intelligence · doi:10.1007/978-3-032-29288-9_2
Mirror, Mirror on the Wall, What’s the Best Model to Install?
Schuster, F., & König, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36885-0_5 · Cited by 1
Uncertainty: Another Aspect to Consider in XAI
Bello, R., Jiménez, Y. M., & Tuyls, K. (2026) · Studies in computational intelligence · doi:10.1007/978-3-032-29288-9_4
Geological Reliability in Deep Learning Mineral Prospectivity Mapping: A Review
Mohamed, T. A. I., Liu, G., Bakheit, A. A., Hussein, H. M., Taha, A. M. M., & Idris, E. O. (2026) · Minerals · doi:10.3390/min16101066
Ramphabana, F., Swana, E. F., & Paepae, T. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8100343
Artificial intelligence in medical sciences: Historical background
Meo, S. A. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45973-3.00014-2
Yan, Z., Jiang, Z., Ma, C., Dong, F., Tong, Z., & Lin, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-42929-2_18
STRUCTURAL MODEL OF AN EXPLANATION TREE FOR INTERPRETING DECISIONS IN AN INTELLIGENT SYSTEM
Chalyi, S. F., & Dementiev, A. (2026) · Bulletin of National Technical University KhPI Series System Analysis Control and Information Technologies · doi:10.20998/2079-0023.2026.02.12
International normative aspects
Troisi, J., & Lombardi, M. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-23677-8.00001-8
Chalyi, S. F., & Dementiev, A. (2026) · Radiotekhnika · doi:10.30837/rt.2026.3.226.01
Metadata
- Authors
- Zhou, J., Gandomi, A. H., Chen, F., & Holzinger, A.
- Affiliations
- University of Technology Sydney (AU)
- Medical University of Graz (AT)
- Corresponding author
- Zhou, Jianlong
- Gandomi, Amir H.
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2021-03-04
- Volume
- 10
- Issue
- 5
- Pages
- 593
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W3133543405
- Cited by
- 606
- References
- 80
- Citations by year
- 2026: 75 · 2025: 138 · 2024: 179 · 2023: 109 · 2022: 84 · 2021: 20
- FWCI
- 34.65
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- OPUS - Open Publications of UTS Scholars (University of Technology Sydney) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- University of Technology Sydney
- Austrian Science Fund (P 32554)
- 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 machine learning, explanation quality evaluation, evaluation metrics, explainability, model-based explanation, example-based explanations, interpretability, fidelity, human-centered evaluation, 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.
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.