A survey on methods and metrics for the assessment of explainability under the proposed AI Act
Open accessAbstract
This study discusses the interplay between metrics used to measure the explainability of the AI systems and the proposed EU Artificial Intelligence Act. A standardisation process is ongoing: several entities (e.g. ISO) and scholars are discussing how to design systems that are compliant with the forthcoming Act and explainability metrics play a significant role. This study identifies the requirements that such a metric should possess to ease compliance with the AI Act. It does so according to an interdisciplinary approach, i.e. by departing from the philosophical concept of explainability and discussing some metrics proposed by scholars and standardisation entities through the lenses of the explainability obligations set by the proposed AI Act. Our analysis proposes that metrics to measure the kind of explainability endorsed by the proposed AI Act shall be risk-focused, model-agnostic, goal-aware, intelligible & accessible. This is why we discuss the extent to which these requirements are met by the metrics currently under discussion.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 required auditability property of Trustworthy AI systems demands the development of practical tools that are capable of verifying desirable properties of neural networks such as stability, sensitivity, relevance or reachability, as well as metrics beyond explainability, such as on traceability, data quality and integrity.
“The required auditability property of Trustworthy AI systems demands the development of practical tools [109] that are capable of verifying desirable properties of neural networks such as stability, sensitivity, relevance or reachability [110], as well as metrics beyond explainability [111-115], such as on traceability, data quality and integrity.”
From Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation (2023) · cites this paper as [115]
Split into 2 atoms — 0 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 1 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
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 · see citing works
Wachter, S., Mittelstadt, B., & Floridi, L. (2017) · International Data Privacy Law · doi:10.1093/idpl/ipx005 · Cited by 1,308 · see citing works
Flagged first, then by citations
Research works printed but not linked: 18
- Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, Pedreschi D. A survey of methods for explaining black box models. ACM computing surveys (CSUR). 2018;51(5):1-42.
- Adadi A, Berrada M. Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE access. 2018;6:52138-60.
- Zhou J, Gandomi AH, Chen F, Holzinger A. Evaluating the quality of machine learning explanations: A survey on methods and metrics. Electronics. 2021;10(5):593.
- Salmon WC. Scientific explanation and the causal structure of the world. Princeton University Press; 1984.
- Van Fraassen BC, et al. The scientific image. Oxford University Press; 1980.
- Achinstein P. The Nature of Explanation. Oxford University Press; 1983.
- Holland JH, Holyoak KJ, Nisbett RE, Thagard PR. Induction: Processes of Inference, Learning, and Discovery. Bradford books. MIT Press; 1989.
- Sellars WS. Philosophy and the Scientific Image of Man. In: Colodny R, editor. Science, Perception, and Reality. Humanities Press/Ridgeview; 1962. p. 35-78.
- Hempel CG, Oppenheim P. Studies in the Logic of Explanation. Philosophy of science. 1948;15(2):135- 75.
- Brun G. Explication as a method of conceptual re-engineering. Erkenntnis. 2016;81(6):1211-41.
- Hilton DJ. Mental models and causal explanation: Judgements of probable cause and explanatory rele- vance. Thinking & Reasoning. 1996;2(4):273-308.
- Wachter S, Mittelstadt B, Russell C. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GPDR. Harv JL & Tech. 2017;31:841.
- Selbst A, Powles J. "Meaningful Information" and the Right to Explanation. In: Conference on Fairness, Accountability and Transparency. PMLR; 2018. p. 48-8.
- Nguyen Ap, Martínez MR. On quantitative aspects of model interpretability. arXiv preprint arXiv:200707584. 2020.
- Lakkaraju H, Kamar E, Caruana R, Leskovec J. Interpretable & explorable approximations of black box models. arXiv preprint arXiv:170701154. 2017.
- Hoffman RR, Mueller ST, Klein G, Litman J. Metrics for explainable AI: Challenges and prospects; 2018. Available from: https://arxiv.org/abs/1812.04608. · arXiv
- Keane MT, Kenny EM, Delaney E, Smyth B. If only we had better counterfactual explanations: Five key deficits to rectify in the evaluation of counterfactual xai techniques. arXiv preprint arXiv:210301035. 2021.
- Sovrano F, Vitali F. An Objective Metric for Explainable AI: How and Why to Estimate the Degree of Explainability. arXiv preprint arXiv:210905327. 2021. Available from: https://arxiv.org/abs/ 2109.05327.
Cited by
Sorted by citations
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101805 · Cited by 1,762 · see citing works
Díaz-Rodríguez, N., Del Ser, J., Coeckelbergh, M., López de Prado, M., Herrera-Viedma, E., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101896 · Cited by 800 · see citing works
EXplainable Artificial Intelligence (XAI)—From Theory to Methods and Applications
Ortigossa, E. S., Gonçalves, T., & Nonato, L. G. (2024) · IEEE Access · doi:10.1109/access.2024.3409843 · Cited by 124 · see citing works
- Authors
- Sovrano, F., Sapienza, S., Palmirani, M., & Vitali, F.
- Affiliations
- University of Bologna (IT)
- Venue
- Frontiers in Artificial Intelligence and Applications
- Publisher
- IOS Press
- Published
- 2021-12-02
- ISSN
- 0922-6389 (ISSN-L)
- 1879-8314
- OpenAlex
- W3207455395
- Cited by
- 27
- References
- 2
- Citations by year
- 2026: 5 · 2025: 9 · 2024: 5 · 2023: 5 · 2022: 2 · 2021: 1
- FWCI
- 5.43
- Type
- book chapter
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Frontiers in artificial intelligence and applications (publishedVersion, cc-by-nc)
- Zurich Open Repository and Archive (University of Zurich) (acceptedVersion, cc-by-nc)
- arXiv (Cornell University) (submittedVersion)
- Archivio istituzionale della ricerca (Alma Mater Studiorum Università di Bologna) (submittedVersion, cc-by-nc)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion, cc-by-nc)
- arXiv (Cornell University)
- Zurich Open Repository and Archive (University of Zurich)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Law › Digitalization, Law, and Regulation
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Keywords
- explainable AI, explainability metrics, EU AI Act, AI compliance, standardization, intelligibility, accessibility
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
