Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists
Open accessThe DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.
Abstract
The growing field of explainable Artificial Intelligence (xAI) has given rise to a multitude of techniques and methodologies, yet this expansion has created a growing gap between existing xAI approaches and their practical application. This poses a considerable obstacle for data scientists striving to identify the optimal xAI technique for their needs. To address this problem, our study presents a customized decision support framework to aid data scientists in choosing a suitable xAI approach for their use-case. Drawing from a literature survey and insights from interviews with five experienced data scientists, we introduce a decision tree based on the trade-offs inherent in various xAI approaches, guiding the selection between six commonly used xAI tools. Our work critically examines six prevalent ante-hoc and post-hoc xAI methods, assessing their applicability in real-world contexts through expert interviews. The aim is to equip data scientists and policymakers with the capacity to select xAI methods that not only demystify the decision-making process, but also enrich user understanding and interpretation, ultimately advancing the application of xAI in practical settings.
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.
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
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
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 4×
“By avoiding the use of overly complex black-box models (Rudin, 2019), data scientists can promote transparency and give users insight into how the model arrives at its predictions.”
InfluentialFrom local explanations to global understanding with explainable AI for trees
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-019-0138-9 · Cited by 10,551 · cited 1×
“Lundberg et al. (2020) also showed that SHAP values are effective in explaining predictions within the medical domain, which further proved the alignment with human intuition.”
Barredo 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 4×
“The flexibility and interpretability of decision trees and GAMs make them accessible to individuals with varying levels of technical knowledge, allowing them to comprehend and benefit from these models in different domains (Arrieta et al., 2020).”
InfluentialScikit-learn: Machine Learning in Python
(2011) · Journal of Machine Learning Research · doi:10.5555/1953048.2078195 · Cited by 8,539
Qualitative Case Study Methodology: Study Design and Implementation for Novice Researchers
Baxter, P., & Jack, S. (2015) · The Qualitative Report · doi:10.46743/2160-3715/2008.1573 · Cited by 7,594
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · arXiv · doi:10.48550/arxiv.1603.02754 · Cited by 7,104
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
Peeking 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
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
Explainable AI: a review of machine learning interpretability methods
Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020) · Entropy · doi:10.3390/e23010018 · Cited by 2,922 · cited 1×
“See Linardatos et al. (2021) for further discussion.”
Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · cited 6×
“Feature importance (implemented with SHAP based on Lundberg and Lee (2017b)), scoped rules (implemented with Anchors based on Ribeiro et al. (2018)), and counterfactuals (implemented with DiCE based on Mothilal et al. (2020)) were chosen as representative post-hoc methods known for their ability to…”
InfluentialA mathematical model of the finding of usability problems
Nielsen, J., & Landauer, T. K. (1993) · Proceedings of the SIGCHI conference on Human factors in computing systems - CHI '93 · doi:10.1145/169059.169166 · Cited by 1,961
Causability and explainability of artificial intelligence in medicine
Holzinger, A., Langs, G., Denk, H., Zatloukal, K., & Müller, H. (2019) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1312 · Cited by 1,885 · cited 1×
“A System Causability Scale (SCS) can be used to determine whether and to what extent an explainable user interface, an explanation, or an explanation process itself is suitable for the intended purpose (Holzinger et al., 2020; Holzinger, Langs et al., 2019).”
Self-citationCan we open the black box of AI?
Castelvecchi, D. (2016) · Nature · doi:10.1038/538020a · Cited by 1,773 · cited 1×
“Due to the growing challenge posed by the so-called ‘‘black box’’ problem (Castelvecchi, 2016) in increasingly complex models of Artificial Intelligence (AI) across various domains, there has been a significant global interest in explainable Artificial Intelligence (xAI) (Con-falonieri, Coba et…”
Explainable AI (XAI): Core Ideas, Techniques, and Solutions
Dwivedi, R., Dave, D., Naik, H., Singhal, S., Omer, R., Patel, P., Qian, B., Wen, Z., Shah, T., Morgan, G., et al. (2023) · ACM Computing Surveys · doi:10.1145/3561048 · Cited by 1,386
Explaining machine learning classifiers through diverse counterfactual explanations
Mothilal, R. K., Sharma, A., & Tan, C. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372850 · Cited by 1,233 · cited 6×
“May lead to infeasible examples (Mothilal et al., 2020).”
InfluentialCounterfactual explanations without opening the black box: automated decisions and the GDPR
Wachter, S., Mittelstadt, B., & Russell, C. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3063289 · Cited by 1,061
Ahmed, I., Jeon, G., & Piccialli, F. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3146552 · Cited by 853 · cited 1×
“Since understanding complex models is essential in the industry, data scientists are therefore more and more focused on developing models that not only provide accurate predictions, but also offer explanations for their decisions (Ahmed et al., 2022).”
Letham, B., Rudin, C., McCormick, T. H., & Madigan, D. (2015) · The Annals of Applied Statistics · doi:10.1214/15-aoas848 · Cited by 766 · cited 6×
“One such scoring system for clinical risk analysis is, for example, CHADS2 (Congestive heart failure, Hypertension, Age, Diabetes, Prior Stroke).”
InfluentialDecision trees: An overview and their use in medicine
Podgorelec, V., Kokol, P., Stiglic, B., & Rozman, I. (2002) · Journal of Medical Systems · doi:10.1023/a:1016409317640 · Cited by 736
Datta, A., Sen, S., & Zick, Y. (2016) · 2016 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2016.42 · Cited by 728 · cited 1×
“One example of this was shown by Datta et al. (2016), where Shapley value-based explanations could contribute to algorithmic transparency.”
Trustworthy Artificial Intelligence: A Review
Kaur, D., Uslu, S., Rittichier, K. J., & Durresi, A. (2023) · ACM Computing Surveys · doi:10.1145/3491209 · Cited by 709 · cited 1×
“In addition to local explanations, understanding the global significance of features is crucial for user confidence in model results and their interpretation (Kaur et al., 2022).”
Trustworthy AI: From Principles to Practices
Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B. (2023) · ACM Computing Surveys · doi:10.1145/3555803 · Cited by 612 · cited 1×
“In any case, trustworthy AI encompasses elements of security (Li et al., 2023), safety, privacy, fairness (Angerschmid et al., 2022), accountability, auditability, and robustness (Holzinger, Dehmer et al., 2022).”
Evaluating the quality of machine learning explanations: a survey on methods and metrics
Zhou, J., Gandomi, A. H., Chen, F., & Holzinger, A. (2021) · Electronics · doi:10.3390/electronics10050593 · Cited by 606 · cited 2×
“Refer to Zhou et al. (2021) for a more exhaustive description and comparison of different evaluation factors for xAI methods.”
Self-citationNauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · ACM Computing Surveys · doi:10.1145/3583558 · Cited by 590 · cited 4×
“As a central aspect of their work, Nauta et al. (2023) provide a classification of 12 essential explanation properties, including concepts such as Compactness and Correctness.”
InfluentialAccurate intelligible models with pairwise interactions
Lou, Y., Caruana, R., Gehrke, J., & Hooker, G. (2013) · Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2487575.2487579 · Cited by 564 · cited 1×
“The GAM classifier was implemented with the InterpretML framework with the default settings (Lou et al., 2013).”
Kaur, H., Nori, H., Jenkins, S., Caruana, R., Wallach, H., & Wortman Vaughan, J. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376219 · Cited by 564
Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey
Buhrmester, V., Münch, D., & Arens, M. (2021) · Machine Learning and Knowledge Extraction · doi:10.3390/make3040048 · Cited by 403
Too much, too little, or just right? Ways explanations impact end users' mental models
Kulesza, T., Stumpf, S., Burnett, M., Yang, S., Kwan, I., & Wong, W.-K. (2013) · 2013 IEEE Symposium on Visual Languages and Human Centric Computing · doi:10.1109/vlhcc.2013.6645235 · Cited by 388 · cited 1×
“Completeness (or coverage) describes the extent to which an explanation covers the relevant aspects and factors that contribute to a model’s decision or prediction (Kulesza et al., 2013).”
FACE: Feasible and Actionable Counterfactual Explanations
Poyiadzi, R., Sokol, K., Santos-Rodriguez, R., De Bie, T., & Flach, P. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375850 · Cited by 317
SHAP and LIME: An Evaluation of Discriminative Power in Credit Risk
Gramegna, A., & Giudici, P. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.752558 · Cited by 306 · cited 1×
“…(Ribeiro et al., 2016) are not bound to specific model architectures, providing explanations that span a wide range of models and offer local explanations that focus on individual predictions or decisions, instead of attempting to explain the entire behavior of the model (Gramegna & Giudici, 2021).”
Multi-Objective Counterfactual Explanations
Dandl, S., Molnar, C., Binder, M., & Bischl, B. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58112-1_31 · Cited by 271
Fairness and Explanation in AI-Informed Decision Making
Angerschmid, A., Zhou, J., Theuermann, K., Chen, F., & Holzinger, A. (2022) · Machine Learning and Knowledge Extraction · doi:10.3390/make4020026 · Cited by 161
Self-citationThe explainability paradox: Challenges for xAI in digital pathology
Evans, T., Retzlaff, C. O., Geißler, C., Kargl, M., Plass, M., Müller, H., Kiehl, T.-R., Zerbe, N., & Holzinger, A. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.03.009 · Cited by 135
Self-citationOn generating trustworthy counterfactual explanations
Del Ser, J., Barredo-Arrieta, A., Díaz-Rodríguez, N., Herrera, F., Saranti, A., & Holzinger, A. (2024) · Information Sciences · doi:10.1016/j.ins.2023.119898 · Cited by 122 · cited 1×
“This not only promotes explainability, but also confidence in the results (Del Ser et al., 2024).”
ResultSelf-citationExplainability and causability in digital pathology
Plass, M., Kargl, M., Kiehl, T., Regitnig, P., Geißler, C., Evans, T., Zerbe, N., Carvalho, R., Holzinger, A., & Müller, H. (2023) · The Journal of Pathology Clinical Research · doi:10.1002/cjp2.322 · Cited by 99
Self-citationBRKAN, M., & BONNET, G. (2020) · European Journal of Risk Regulation · doi:10.1017/err.2020.10 · Cited by 63
Cited by
Mathew, D. E., Ebem, D. U., Ikegwu, A. C., Ukeoma, P. E., & Dibiaezue, N. F. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11732-2 · Cited by 168
Darvishvand, L., Kamkari, B., Huang, M. J., & Hewitt, N. J. (2025) · Sustainable Cities and Society · doi:10.1016/j.scs.2025.106492 · Cited by 42
Kabir, S., Hossain, M. S., & Andersson, K. (2025) · Algorithms · doi:10.3390/a18090556 · Cited by 44
Qureshi, M. A., Noor, A. A., Manzoor, A., Mazhar Qureshi, M. D., Younus, A., & Rashwan, W. (2026) · PLOS One · doi:10.1371/journal.pone.0351473 · Cited by 7
Metadata
- Authors
- Retzlaff, C. O., Angerschmid, A., Saranti, A., Schneeberger, D., Röttger, R., Müller, H., & Holzinger, A.
- Venue
- Cognitive Systems Research
- Publisher
- Elsevier BV
- Published
- 2024-08
- Volume
- 86
- Pages
- 101243
- ISSN
- 1389-0417 (ISSN-L)
- OpenAlex
- W4396668454
- Cited by
- 194
- References
- 39
- FWCI
- 28.87
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.