"Why Should I Trust You?": Explaining the Predictions of Any Classifier
The DOI matches its Crossref record; 35 of the 36 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“In the perturbation-based approaches, a portion of the input is changed and the effect of this change on the model output is observed [170–173].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [172]
In the citing paper
“For the time being however, “[d]espite widespread adoption, machine learning models remain mostly black boxes” (Ribeiro, Singh, and Guestrin 2016, 1135).”
From Accountable Artificial Intelligence: Holding Algorithms to Account (2021) · cites this paper as Ribeiro, Singh, and Guestrin 2016
In the citing paper
“In particular, local explanations that explain the rationale for a single prediction (in contrast to global explanations describing the overall logic of the model) are recommended to help people judge whether to trust a model on a case-by-case basis [28].”
From Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making (2020) · cites this paper as [28]
In the citing paper
“This stands in contrast to the findings of [28] where explanations helped expose a critical flaw in the model (treating snow as Husky), which could help the debugging work.”
From Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making (2020) · cites this paper as [28]
In the citing paper
“Integrated Gradients [16] and LIME [11] provide input attribution but require model access.”
From AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation (2025) · cites this paper as [11]
45 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
The magical number seven, plus or minus two: Some limits on our capacity for processing information.
Miller, G. A. (1994) · Psychological Review · doi:10.1037/0033-295x.101.2.343 · Cited by 17,161
Efron, B., Hastie, T., Johnstone, I., & Tibshirani, R. (2004) · The Annals of Statistics · doi:10.1214/009053604000000067 · Cited by 9,357
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
A threshold of ln n for approximating set cover
Feige, U. (1998) · Journal of the ACM · doi:10.1145/285055.285059 · Cited by 3,086
(2007) · Cited by 2,018
Explaining collaborative filtering recommendations
Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000) · Proceedings of the 2000 ACM conference on Computer supported cooperative work · doi:10.1145/358916.358995 · Cited by 1,731
Research works printed but not linked: 2
- 10.5555/1462129 · doi:10.5555/1462129
- 10.5555/2969442.2969519 · doi:10.5555/2969442.2969519
Cited by
Items 1,001–1,020 of 1,020
Sanity Checks for Saliency Metrics
Tomsett, R., Harborne, D., Chakraborty, S., Gurram, P., & Preece, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.6064 · Cited by 3
On Measuring Faithfulness or Self-consistency of Natural Language Explanations
Parcalabescu, L., & Frank, A. (2023) · arXiv · doi:10.48550/arxiv.2311.07466 · Cited by 27
“In Section 2.1 we defined faithfulness according to Harrington et al. (1985); Ribeiro et al. (2016); Jacovi and Goldberg (2020), namely: a faithful explanation accurately represents the true reasoning process behind the model’s prediction .”
InfluentialNomological Deductive Reasoning for Trustworthy, Human-Readable, and Actionable AI Outputs
Hakizimana, G., & Ledezma Espino, A. (2025) · Algorithms · doi:10.3390/a18060306 · Cited by 2
Interpreting pretrained speech models for automatic speech assessment of voice disorders
Lau, H. S., Huntly, M., Morgan, N., Iyenoma, A., Zeng, B., & Bashford, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-67278-1_5 · Cited by 2
Díaz-Rodríguez, N., Lamas, A., Sanchez, J., Franchi, G., Donadello, I., Tabik, S., Filliat, D., Cruz, P., Montes, R., & Herrera, F. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.09.022 · Cited by 2
EMERSK -- Explainable Multimodal Emotion Recognition with Situational Knowledge
Palash, M., & Bhargava, B. (2023) · arXiv · doi:10.48550/arxiv.2306.08657 · Cited by 25
“Various methods have been proposed to generate explanations of deep learning models, including Saliency Map [11], Grad-CAM [12], SHAP [13], and LIME [14].”
MethodLayLens: Improving Deepfake Understanding through Simplified Explanations
Narang, A., Gupta, P., Su, L., & Dhall, A. (2025) · Proceedings of the 27th International Conference on Multimodal Interaction · doi:10.1145/3716553.3757093 · Cited by 1
Rehman, U. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1924913 · Cited by 1
Bohlen, L., Rosenberger, J., Hambauer, N., Zähringer, D., Franz, V., Zschech, P., & Kraus, M. (2026) · Health Care Management Science · doi:10.1007/s10729-026-09760-y
Explainability of decoder-only clinical large language models: A scoping review
Mishra, N., Abu-Hanna, A., & Calixto, I. (2026) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2026.103501
Explainable Anomaly Detection for System Logs in Distributed Environments
Gu, Z., Yue, W., & Liu, C. (2026) · Computers, Materials & Continua · doi:10.32604/cmc.2026.077388
Mohamed, A. S., Fritz, C., Saber, A. M., Ma, Y., Kaur, R., Al-Darwbi, M., Friedrich, D., & Kundur, D. (2026) · arXiv · doi:10.48550/arxiv.2609.00171
“2) Local Interpretable Model-Agnostic Explanations (LIME): Local Interpretable Model-Agnostic Explanations (LIME) [160] is an associative, local, model-agnostic explanation technique designed to explain individual predictions of complex models by approximating the model locally with an…”
AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation
Horovicz, M. (2025) · arXiv · doi:10.48550/arxiv.2512.12597
“Integrated Gradients [16] and LIME [11] provide input attribution but require model access.”
Algorithmic monoculture and social welfare
(2023) · The Societal Impacts of Algorithmic Decision-Making · doi:10.1145/3603195.3603202
Explainable and Interpretable AI for Voice and Speech Analysis in Clinical Care: Systematic Review
Ebraheem, M., Toghranegar, J., Bridge2AI-Voice Consortium, Bensoussan, Y., & Templeton, J. M. (2026) · Journal of Medical Internet Research · doi:10.2196/83790
AI interventions as hypothesis cues: rethinking overreliance in human-AI decision-making
Pham, M. P., Illingworth-Vera, D. A., & Thomas, R. P. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1967356
Santana-Velásquez, A., & Salazar-Sánchez, M. B. (2026) · Computers · doi:10.3390/computers15080506
Hussain, A. B., & Sun, J. (2026) · Journal of Forecasting · doi:10.1002/for.70193
Explainable AI for employee turnover prediction: a SHAP-based intelligent analytics approach
Jia, H. (2026) · Scientific Reports · doi:10.1038/s41598-026-60901-3
Multimorbidity Measurement Strategies for Predicting Hospital Visits
Neves, B., Moreira, J. M., Gonçalves, S., Cerejo, J., Mota, I., Silva, N. A., Leite, F., & Silva, M. J. (2025) · doi:10.21203/rs.3.rs-6515465/v1
Metadata
- Authors
- Ribeiro, M. T., Singh, S., & Guestrin, C.
- Affiliations
- University of Washington, Seattle, WA, USA
- University of Washington (US)
- Venue
- Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2016-08-13
- Pages
- 1135-1144
- OpenAlex
- W2282821441
- Semantic Scholar
- c0883f5930a232a9c1ad601c978caede29155979
- Cited by
- 17,555
- References
- 36
- Citations by year
- 2026: 3181 · 2025: 3064 · 2024: 2256 · 2023: 2067 · 2022: 1777 · 2021: 2158 · 2020: 1491 · 2019: 907 · 2018: 462 · 2017: 153 · 2016: 27
- FWCI
- 278.74
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- Funders
- Defense Sciences Office, DARPA
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Keywords
- explainable machine learning, model interpretability, trust in predictions, black-box models, trustworthy AI
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.