Philosophy of science at sea: Clarifying the interpretability of machine learning
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
In computer science, there are efforts to make machine learning more interpretable or explainable, and thus to better understand the underlying models, algorithms, and their behavior. But what exactly is interpretability, and how can it be achieved? Such questions lead into philosophical waters because their answers depend on what explanation and understanding are—and thus on issues that have been central to the philosophy of science. In this paper, we review the recent philosophical literature on interpretability. We propose a systematization in terms of four tasks for philosophers: (i) clarify the notion of interpretability, (ii) explain the value of interpretability, (iii) provide frameworks to think about interpretability, and (iv) explore important features of it to adjust our expectations about it.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 4×
“…can be used for pedagogical purposes and enable users to make predictions about the behavior of the ML model in question, the authors take the use of simplified models to be problematic because, due to approximations and ideal-izations, models typically get something wrong (see also Rudin, 2019).”
BackgroundInfluentialPeeking 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
Lipton, 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
Studies in the Logic of Explanation
Hempel, C. G., & Oppenheim, P. (1948) · Philosophy of Science · doi:10.1086/286983 · Cited by 3,174
Explaining Explanations: An Overview of Interpretability of Machine Learning
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018) · 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2018.00018 · Cited by 2,507 · cited 1×
“Many of the recent successes of ML come from deep learning and are based on deep neural networks (DNNs; Goodfellow et al., 2016; LeCun et al., 2015).”
BackgroundDefinitions, methods, and applications in interpretable machine learning
Murdoch, W. J., Singh, C., Kumbier, K., Abbasi-Asl, R., & Yu, B. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1900654116 · Cited by 2,167 · cited 2×
“Murdoch et al. (2019, p. 22071) claim that there is “considerable confusion about the notion of interpretability.””
BackgroundMachine Learning Interpretability: A Survey on Methods and Metrics
Carvalho, D. V., Pereira, E. M., & Cardoso, J. S. (2019) · Electronics · doi:10.3390/electronics8080832 · Cited by 1,842 · cited 1×
“Interpretability has thus become an important research topic in computer science (e.g., Carvalho et al., 2019; Chakraborty et al., 2017; Reyes et al., 2020).”
BackgroundExplanation and Scientific Understanding
Friedman, M. (1974) · The Journal of Philosophy · doi:10.2307/2024924 · Cited by 1,386 · cited 1×
“Miller's focus is on explanation – a classical topic in philosophy of science (see Friedman, 1974; Hempel & Oppenheim, 1948; Kitcher, 1981; Lewis, 1986; Woodward, 2003, for famous philosophical accounts of explanation; Woodward & Ross, 2021 for an excellent survey).”
BackgroundMittelstadt, B., Russell, C., & Wachter, S. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287574 · Cited by 794 · cited 1×
“As Mittelstadt et al. (2019) report, simplified models of ML models pervade much work on interpretability and explainable AI.”
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 · cited 4×
“synonymously with “interpretable” (see Gilpin et al., 2018, p. 80) and figures prominently in the buzzword “explaina-ble AI” (XAI, cf. Adadi & Berrada, 2018).”
BackgroundInfluentialSolving the Black Box Problem: A Normative Framework for Explainable Artificial Intelligence
Zednik, C. (2021) · Philosophy & Technology · doi:10.1007/s13347-019-00382-7 · Cited by 419
The philosophical novelty of computer simulation methods
Humphreys, P. (2009) · Synthese · doi:10.1007/s11229-008-9435-2 · Cited by 362
Elgin, C. (2007) · Philosophical Studies · doi:10.1007/s11098-006-9054-z · Cited by 309
Cited by
Artificial Epistemic Authorities
Hauswald, R. (2025) · Social Epistemology · doi:10.1080/02691728.2025.2449602 · Cited by 46
“Despite considerable progress in this program, however, it is not yet clear whether and how the opacity of AI can be sufficiently overcome (see Beisbart and Räz 2022 for a more detailed discussion).”
Predicting and explaining with machine learning models: Social science as a touchstone
Buchholz, O., & Grote, T. (2023) · Studies in History and Philosophy of Science · doi:10.1016/j.shpsa.2023.10.004 · Cited by 15
AI and the Philosophy of Expertise and Epistemic Authority
Hauswald, R. (2025) · A Companion to Applied Philosophy of AI · doi:10.1002/9781394238651.ch5 · Cited by 5
Metadata
- Authors
- Beisbart, C., & Räz, T.
- Venue
- Philosophy Compass
- Publisher
- Wiley
- Published
- 2022-04-19
- Volume
- 17
- Issue
- 6
- ISSN
- 1747-9991 (ISSN-L)
- OpenAlex
- W4224271529
- Cited by
- 58
- References
- 16
- FWCI
- 4.20
- 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.