The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Against Interpretability: a Critical Examination of the Interpretability Problem in Machine Learning
Open accessAbstract
The usefulness of machine learning algorithms has led to their widespread adoption prior to the development of a conceptual framework for making sense of them. One common response to this situation is to say that machine learning suffers from a “black box problem.” That is, machine learning algorithms are “opaque” to human users, failing to be “interpretable” or “explicable” in terms that would render categorization procedures “understandable.” The purpose of this paper is to challenge the widespread agreement about the existence and importance of a black box problem. The first section argues that “interpretability” and cognates lack precise meanings when applied to algorithms. This makes the concepts difficult to use when trying to solve the problems that have motivated the call for interpretability (etc.). Furthermore, since there is no adequate account of the concepts themselves, it is not possible to assess whether particular technical features supply formal definitions of those concepts. The second section argues that there are ways of being a responsible user of these algorithms that do not require interpretability (etc.). In many cases in which a black box problem is cited, interpretability is a means to a further end such as justification or non-discrimination. Since addressing these problems need not involve something that looks like an “interpretation” (etc.) of an algorithm, the focus on interpretability artificially constrains the solution space by characterizing one possible solution as the problem itself. Where possible, discussion should be reformulated in terms of the ends of interpretability.
Overview
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
Verification
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.
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
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
The ethics of algorithms: Mapping the debate
Mittelstadt, B. D., Allo, P., Taddeo, M., Wachter, S., & Floridi, L. (2016) · Big Data & Society · doi:10.1177/2053951716679679 · Cited by 4,567 · cited 3×
“Yet both the position that one needs to “ oversee ” epistemic processes in order to be responsible in relying on their results (Mittelstadt et al. 2016; Tutt 2016) and the position that “ oversight ” requires an interpretation of one ’ s instruments leave no room for alternative ways of thinking…”
BackgroundHow the machine “thinks”: Understanding opacity in machine learning algorithms
Burrell, J. (2016) · Big Data & Society · doi:10.1177/2053951715622512 · Cited by 3,196 · cited 1×
“Another way of trying to define interpretability is to identify its causes or grounds, such as a mismatch between how people think and the requirements of mathematical optimization (Burrell 2016).”
BackgroundStudies in the Logic of Explanation
Hempel, C. G., & Oppenheim, P. (1948) · Philosophy of Science · doi:10.1086/286983 · Cited by 3,174
Towards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Explanation and Scientific Understanding
Friedman, M. (1974) · The Journal of Philosophy · doi:10.2307/2024924 · Cited by 1,386 · cited 1×
“Hempel and Oppenheim ’ s seminal “ Studies in the Logic of Explanation ” (1948) initiated a debate that subsequently included diverse contributions from Salmon (1984, 1989), van Fraassen (1977), Kitcher (1976, 1989), and Friedman (1974), among others.”
BackgroundGoldman, A. I. (1967) · The Journal of Philosophy · doi:10.2307/2024268 · Cited by 925
Experts: Which Ones Should You Trust?
GOLDMAN, A. I. (2001) · Philosophy and Phenomenological Research · doi:10.1111/j.1933-1592.2001.tb00093.x · Cited by 911
The Epistemic Significance of Disagreement
Kelly, T. (2005) · Oxford Studies In Epistemology · doi:10.1093/oso/9780199285891.003.0007 · Cited by 598
The ethics of information transparency
Turilli, M., & Floridi, L. (2009) · Ethics and Information Technology · doi:10.1007/s10676-009-9187-9 · Cited by 419
Cited by
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Ser, J. D., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., et al. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102301 · Cited by 626
Langer, M., Oster, D., Speith, T., Hermanns, H., Kästner, L., Schmidt, E., Sesing, A., & Baum, K. (2021) · Artificial Intelligence · doi:10.1016/j.artint.2021.103473 · Cited by 652
Interpretable Machine Learning: Moving from mythos to diagnostics
Chen, V., Li, J., Kim, J. S., Plumb, G., & Talwalkar, A. (2021) · Queue · doi:10.1145/3511299 · Cited by 516
Ferreira, C., & Gonçalves, G. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.05.010 · Cited by 417
Open Problems in Mechanistic Interpretability
Sharkey, L., Chughtai, B., Batson, J., Lindsey, J., Wu, J., Bushnaq, L., Goldowsky-Dill, N., Heimersheim, S., Ortega, A., Bloom, J., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.16496 · Cited by 291
Metadata
- Authors
- Krishnan, M.
- Venue
- Philosophy & Technology
- Published
- 2019-08-13
- Volume
- 33
- Issue
- 3
- Pages
- 487-502
- ISSN
- 2210-5433 (ISSN-L)
- 2210-5441
- OpenAlex
- W2968611394
- Cited by
- 218
- References
- 10
- FWCI
- 8.75
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Against Interpretability: a Critical Examination of the Interpretability Problem in Machine Learning. https://app.cochat.ai/papers/10.1007/s13347-019-00372-9
- The paper
- Krishnan, M. (2020). Against Interpretability: a Critical Examination of the Interpretability Problem in Machine Learning. Philosophy & Technology. https://doi.org/10.1007/s13347-019-00372-9
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.