The DOI matches its Crossref record; 24 of the 25 references it cites were found in a registry or an index, and 1 are not checked yet.
The Mythos of Model Interpretability: In machine learning, the concept of interpretability is both important and slippery.
Open accessAbstract
Supervised machine-learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world?
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.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Newer methodologies have the danger of becoming more complex and less interpretable, even when sophisticated interpretation technique are used11.”
From Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist. (2020) · cites this paper as [11]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As users of these systems have grown beyond ML experts and the research community, the need to better interpret and understand them has grown as well, particularly in the context of high-stakes decisions that affect individuals ' health or wellbeing (Lakkaraju et al., 2016; Lipton, 2018; Rudin, 2019).”
From Explainable machine learning for public policy: Use cases, gaps, and research directions (2023) · cites this paper as Lipton, 2018
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“While this expansion of the field has yielded a rich body of methodological work, recently, the community has begun to highlight the shortfalls such as the lack of consistent language and definitions, the lack of clearly defined explainability goals, and desiderata; and the lack of consensus on metrics and methods of evaluating the quality of explanations (Doshi-Velez and Kim, 2017; Lipton, 2018;”
From Explainable machine learning for public policy: Use cases, gaps, and research directions (2023) · cites this paper as Lipton, 2018
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For her, as for other people who are not AI specialists, it may be better to employ natural language, narrative, explanation by example, visualisations, and so forth (Barredo Arrieta et al., 2020;Borrego-Díaz & Galán-Páez, 2022;Lipton, 2018).”
From Hidden Risks: Artificial Intelligence and Hermeneutic Harm (2025) · cites this paper as Lipton, 2018
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“According to Lipton [121], a model is transparent if its intrinsic structure satisfies at least one of the following three requirements:”
From A Survey on Explainable Anomaly Detection (2024) · cites this paper as [121]
The cited source says what the claim attributes to it.
In the citing paper
“Unfortunately, scarce contributions have attempted to define such goals from a conceptual perspective [5, 13, 24, 30].”
From Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI (2020) · cites this paper as [5]
The cited source says what the claim attributes to it.
In the citing paper
“However, it misses to consider other purposes motivating the need for interpretable AI models, such as causality, transferability, informativeness, fairness and confidence [5, 24, 25, 26].”
From Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI (2020) · cites this paper as [5]
The cited source says what the claim attributes to it.
In the citing paper
“Therefore, post-hoc explanation techniques are employed to explain existing models (Došilović et al., 2018; Lipton, 2018).”
From Effects of Explainable Artificial Intelligence on trust and human behavior in a high-risk decision task (2023) · cites this paper as Lipton, 2018
The cited source says what the claim attributes to it.
In the citing paper
“As explainability is not a monolithic concept and can play different roles in different applications (Lipton, 2018; Molnar, 2019), this process requires extensive domain/application-specific efforts.”
From Explainable machine learning for public policy: Use cases, gaps, and research directions (2023) · cites this paper as Lipton, 2018
The cited source says what the claim attributes to it.
In the citing paper
“Too great an emphasis on making explanations psychologically fitting risks making it easier for bad actors to deceive and manipulate end-users (Baron, 2023;Lipton, 2018, pp. 21-22).”
From Hidden Risks: Artificial Intelligence and Hermeneutic Harm (2025) · cites this paper as Lipton, 2018
The cited source says what the claim attributes to it.
In the citing paper
“While providing individuals with grounds to contest individual decisions is often cited as a central motivation of the field of explainable artificial intelligence (XAI) (Ribeiro, Singh, and Guestrin 2016;Lipton 2018;Adadi and Berrada 2018;Molnar 2020), only very few technical works address contestability in greater detail (Mansi, Karusala, and Riedl 2025).”
From Explainable AI Isn't Enough! Rethinking Algorithmic Contestability (2026) · cites this paper as Lipton 2018
The cited source says what the claim attributes to it.
In the citing paper
“Interpretability and explainability methods promoted by popular tools vary widely in their goals [120] and, like many 'snake oil' AI products [18, 59, 91], may encourage false confidence in their users [118].”
From Towards AI Accountability Infrastructure: Gaps and Opportunities in AI Audit Tooling (2025) · cites this paper as [120]
The cited source says what the claim attributes to it.
In the citing paper
“In interpretable AI research, the motivations and methods employed are often described as”
From Open Problems in Mechanistic Interpretability (2025) · cites this paper as Lipton, 2018
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“With the availability of more datasets, there is an increased benefit that allows more complex functions to be approximated for future developments in XAI [21,167].”
From Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence (2024) · cites this paper as [167]
Experimental — accuracy not yet measuredIn the citing paper
“Clinical tasks are often complex and it is impossible to incorporate and evaluate all desirable properties (e.g. legality, ethicality, and robustness) in a model using standard predictive performance evaluation metrics (e.g. area under the receiver-operating curve) [12].”
In the citing paper
“Researchers do not specify what terms mean, use the same term for different meanings, or refer to the same notion by different terms.”
In the citing paper
“Lipton [12] points out that these terms are often ill-defined in the existing literature.”
In the citing paper
“These explanations have the potential to present plausible but misleading explanations [12, 75].”
In the citing paper
“However, it is important to note that ML models are not designed to identify causal relationships but rather association relationships 116 .”
From Machine learning in concrete science: applications, challenges, and best practices (2022) · cites this paper as [116]
In the citing paper
“Hence, trust in ML models is strongly related to their interpretability, which has thus become a focus of active research in the ML community 116,132 .”
From Machine learning in concrete science: applications, challenges, and best practices (2022) · cites this paper as [116]
In the citing paper
“As the field is still in its infancy, there is no consensus on the definition of the terms interpretability and explainability in this context, and recently various definitions have been proposed for these terms [9,88,110].”
From Transparency of deep neural networks for medical image analysis: A review of interpretability methods (2022) · cites this paper as [88]
In the citing paper
“Lipton [147], however, notes that even white-box models might not be interpretable anymore when their size exceed the limited capacity of human cognition”
From From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2023) · cites this paper as [147]
In the citing paper
“We also considered the ethical implications of AI in preserving privacy and the necessity for transparency, oversight, and continuous evaluation of AI systems [52][53][54].”
From Fairness and Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, and Mitigation Strategies (2023) · cites this paper as [52]
In the citing paper
“XAI can be used to help us evaluate if predictions are biased and defend algorithmic decisions as being fair and ethical [18,19,46,66].”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [46]
In the citing paper
“Although, giving explanations can increase understanding of and trust in a system [19,46,64], simple explanations can hide undesirable attributes of the system and may mislead users into coming to dangerous or unfounded conclusions that could ultimately be unethical [21].”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [46]
In the citing paper
“Additionally, XAI can help to shed some light onto causality [18,46,67] although, there is a recognized need to go beyond causality/correlation to true “causability” [3].”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [46]
In the citing paper
“However, linear models, for example, are not strictly more interpretable than, for example, neural networks, especially when high-dimensional or heavily engineered features are used.”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [46]
In the citing paper
“On the other hand, there are some studies supporting that XAI is not always necessary [46,134,135].”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [46]
In the citing paper
“Lipton [46] argues that the short-term goal of building trust with doctors by developing transparent models might clash with the longer-term goal of improving health care.”
From Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021) · cites this paper as [46]
In the citing paper
“Lipton (2018) [31] and Gunning et al. (2019) [32] highlight that for AI to be effectively integrated into clinical practice, it must provide clear and interpretable explanations of its outputs.”
From Leading with AI in critical care nursing: challenges, opportunities, and the human factor (2024) · cites this paper as Lipton (2018) [31]
In the citing paper
“However, at this level of abstraction, explainability may be difficult to reach even to computer scientists and engineers (Lipton 2018).”
From Transparency as design publicity: explaining and justifying inscrutable algorithms (2021) · cites this paper as Lipton 2018
In the citing paper
“The proposed approach to algorithmic transparency deviates from the existing body of literature on explainable artificial intelligence (xAI), where the concept of transparency focuses on the explanation of the inner workings of algorithms or the interpretability of their individual outcomes (Lipton 2018; Ribeiro et al. 2016).”
From Transparency as design publicity: explaining and justifying inscrutable algorithms (2021) · cites this paper as Lipton 2018
In the citing paper
“This suggests a disconnect between organizational realities and current research, which undermines advancements [197,287].”
From Fairness in machine learning: A survey (2024) · cites this paper as [197]
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
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482
(2008) · Journal of Machine Learning Research · Cited by 33,051
"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
Causality: Models, Reasoning, and Inference
Pearl, J. (2009) · doi:10.1017/cbo9780511803161 · Cited by 11,653
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
Dueling Network Architectures for Deep Reinforcement Learning
Wang, Z., Schaul, T., Hessel, M., van Hasselt, H., Lanctot, M., & de Freitas, N. (2015) · arXiv · doi:10.48550/arxiv.1511.06581 · Cited by 3,300
Fair prediction with disparate impact: a study of bias in recidivism prediction instruments
Chouldechova, A. (2017) · Big Data · doi:10.1089/big.2016.0047 · Cited by 2,159
European Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
Goodman, B., & Flaxman, S. (2017) · AI Magazine · doi:10.1609/aimag.v38i3.2741 · Cited by 2,131 · cited 2×
“Few would suggest that a human could contemplate a thousand parameters at once, but most could simulate a linear model with 20 parameters.”
Background(2009) · Cited by 1,900
Understanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission
Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., & Elhadad, N. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2788613 · Cited by 1,685
Hidden factors and hidden topics
McAuley, J., & Leskovec, J. (2013) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/2507157.2507163 · Cited by 1,565
Inceptionism: Going Deeper into Neural Networks
Mordvintsev, A., Olah, C., & Tyka, M. (2015) · Cited by 574
Accurate 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 2×
“Our investigation of”
BackgroundIntelligible models for classification and regression
Lou, Y., Caruana, R., & Gehrke, J. (2012) · Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2339530.2339556 · Cited by 547
Huysmans, J., Dejaeger, K., Mues, C., Vanthienen, J., & Baesens, B. (2011) · Decision Support Systems · doi:10.1016/j.dss.2010.12.003 · Cited by 425
Legibility and predictability of robot motion
Dragan, A. D., Lee, K. C. T., & Srinivasa, S. S. (2013) · doi:10.5555/2447556.2447672 · Cited by 346
An empirical study of machine learning techniques for affect recognition in human–robot interaction
Rani, P., Liu, C., Sarkar, N., & Vanman, E. (2006) · Pattern Analysis and Applications · doi:10.1007/s10044-006-0025-y · Cited by 313
Wang, H.-X., Fratiglioni, L., Frisoni, G. B., Viitanen, M., & Winblad, B. (1999) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a009864 · Cited by 110
Case-based explanation of non-case-based learning methods.
Caruana, R., Kangarloo, H., Dionisio, J. D. N., Sinha, U., & Johnson, D. (1999) · PubMed Central · Cited by 92
Interactive and interpretable machine learning models for human machine collaboration
Kim, B. (2015) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 83
Learning From Explanations Using Sentiment and Advice in RL
Krening, S., Harrison, B. E., Feigh, K. M., Isbell, C. L., Riedl, M. O., & Thomaz, A. L. (2016) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2016.2628365 · Cited by 83
An empirical study of machine learning techniques for affect recognition in human-robot interaction
Liu, C., Rani, P., & Sarkar, N. (2005) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2005.1545344 · Cited by 67
(2015) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 34
Flagged first, then by citations
Research works printed but not linked: 9
- Athey S. Imbens G. W. 2015 Machine-learning methods https://arxiv.org/abs/1504.01132v1 (see also ref. 7). Athey S. Imbens G. W. 2015 Machine-learning methods https://arxiv.org/abs/1504.01132v1 (see also ref. 7). · arXiv
- Caruana R., 1999, Proceedings of the American Medical Informatics Association (AMIA) Symposium: 212-215
- Chang J., 2009, Proceedings of the 22nd International Conference on Neural Information Processing Systems (NIPS), 288-296
- Doshi-Velez F., 2015, Proceedings of the 29th Association for the Advancement of Artificial Intelligence (AAAI) Conference, 2575-2581
- Kim B., 2014, Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS), 2, 1952
- Lipton Z. C., 2016, Proceedings of Machine Learning for Healthcare.
- Mikolov T., 2013, Proceedings of the 26th International Conference on Neural Information Processing Systems (NIPS), 2
- Ridgeway G., 1998, Proceedings of the 4th International Conference on Knowledge Discovery and Data Mining: 101-104
- 10.5555/3045390.3045601 · DOI
Cited by
Sorted by citations
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
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
A Comprehensive Survey on Transfer Learning
Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3004555 · Cited by 6,678
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
“In other words, for the field to progress, it should be supported by a standalone research community who, at this stage of advancement, should mainly be engaged towards more formalism in terms of: (i) Systematic definitions: depending on their background, researchers use synonymously concepts that are semantically dif…”
BackgroundMethodInfluentialExplanation 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
Metadata
- Authors
- Lipton, Z. C.
- Affiliations
- Carnegie Mellon University (US)
- Corresponding author
- Lipton, Zachary C.
- ORCID
- Lipton, Zachary C.
- Venue
- Queue
- Published
- 2018-06
- Volume
- 16
- Issue
- 3
- Pages
- 31-57
- ISSN
- 0001-0782 (ISSN-L)
- 1542-7730
- 1542-7749
- OpenAlex
- W2439568532
- Cited by
- 5,427
- References
- 25
- Citations by year
- 2026: 803 · 2025: 918 · 2024: 633 · 2023: 657 · 2022: 575 · 2021: 664 · 2020: 521 · 2019: 395 · 2018: 190
- FWCI
- 249.23
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Communications of the ACM (publishedVersion)
- Queue (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- model interpretability, explainable AI, machine learning 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
