--- title: "\"Why Should I Trust You?\" — Ribeiro 2016" description: "Machine learning models often act as black boxes, which makes it hard to decide whether to act on a single prediction or to deploy a whole model." authors: ["Marco Tulio Ribeiro", "Sameer Singh", "Carlos Guestrin"] year: 2016 venue: "arXiv:1602.04938" source: "https://arxiv.org/abs/1602.04938" doi: "10.48550/arxiv.1602.04938" arxiv: "1602.04938" licence: "arXiv — non-exclusive licence to distribute" licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/ribeiro-2016-why-should-i-trust-explaining/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ribeiro-2016-why-should-i-trust-explaining/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/) / "Why Should I Trust You?": Explaining the Predictions of Any Classifier # "Why Should I Trust You?": Explaining the Predictions of Any Classifier **Authors:** [Marco Tulio Ribeiro](https://md.research.elamur.ai/free/en/authors/marco-tulio-ribeiro/), [Sameer Singh](https://md.research.elamur.ai/free/en/authors/sameer-singh/), [Carlos Guestrin](https://md.research.elamur.ai/free/en/authors/carlos-guestrin/) · **Year:** 2016 · **Venue:** arXiv:1602.04938 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/1602.04938) · [PDF](https://arxiv.org/pdf/1602.04938) · [DOI 10.48550/arxiv.1602.04938](https://doi.org/10.48550/arxiv.1602.04938) · [arXiv 1602.04938](https://arxiv.org/abs/1602.04938) · [OpenAlex](https://openalex.org/W2951501516) **Citations:** 332 citations (openalex-snapshot · 2026-10-14) · [816](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Machine learning models often act as black boxes, which makes it hard to decide whether to act on a single prediction or to deploy a whole model. The authors introduce LIME (Local Interpretable Model-agnostic Explanations). It treats any classifier or regressor as a black box. To explain one prediction, it perturbs the instance in an interpretable representation, such as the presence or absence of words or image superpixels. It then fits a simple, sparse linear surrogate model, weighted by how close each perturbed sample is to the original. A second method, SP-LIME, frames the choice of a small, non-redundant set of explained examples as submodular optimization, which gives a global picture of the model. The authors test both methods on text classifiers (including random forests) and on image neural networks, in simulated studies and with human subjects. Explanations helped people, including non-experts, choose the classifier that generalizes better, find spurious features caused by data leakage or dataset shift, and fix weak models. This matters because explanations offer a check on trust that goes beyond validation accuracy. ## Key points - LIME balances two goals: local fidelity, meaning it matches the model near the instance being explained, and interpretability, meaning it keeps the explanation short. It needs no access to the model's internals. - SP-LIME uses greedy submodular selection to choose representative instances, so users don't have to inspect a large dataset at random. - On the 20 newsgroups "Christianity vs Atheism" task, a classifier with higher validation accuracy turned out to depend on meaningless artifacts such as header words. Non-expert users who removed features based on LIME explanations produced a classifier that generalized better. - Crowd workers given SP-LIME explanations picked the model that generalizes better about 89% of the time. This figure comes from my knowledge of the paper; the provided excerpt omitted the results section. - The authors also explain image predictions from a neural network (Google's Inception). Planned future work includes other explanation families such as decision trees, a pick step for images, and faster explanations. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Other](https://md.research.elamur.ai/free/en/shelves/other/) ## Cited by Cited by 816 papers of our library cite it (of the 140673 whose bibliographies we read); 48 of them have a page here, 768 not yet. - [Evaluation of Adversarial Robustness in Arabic Language Models](https://md.research.elamur.ai/free/en/papers/alajmi-2026-evaluation-adversarial-robustness-arabic-language/) - [Arabic Tweet Act: A Weighted Ensemble Pre-Trained Transformer Model for Classifying Arabic Speech Acts on Twitter](https://md.research.elamur.ai/free/en/papers/alshehri-2024-arabic-tweet-act-weighted-ensemble/) - [Arabic Sentiment Analysis with Noisy Deep Explainable Model](https://md.research.elamur.ai/free/en/papers/atabuzzaman-2023-arabic-sentiment-analysis-noisy-deep/) - [Interpretable Neural Predictions with Differentiable Binary Variables](https://md.research.elamur.ai/free/en/papers/bastings-2019-interpretable-neural-predictions-differentiable-binary/) - [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://md.research.elamur.ai/free/en/papers/burns-2023-weak-strong-generalization-eliciting-strong/) - [e-SNLI: Natural Language Inference with Natural Language Explanations](https://md.research.elamur.ai/free/en/papers/camburu-2018-e-snli-natural-language-inference/) - [FLUTE: Figurative Language Understanding through Textual Explanations](https://md.research.elamur.ai/free/en/papers/chakrabarty-2022-flute-figurative-language-understanding-through/) - [Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-paragraph-level-rationale-extraction-through/) - [A Survey of the State of Explainable AI for Natural Language Processing](https://md.research.elamur.ai/free/en/papers/danilevsky-2020-survey-state-explainable-ai-natural/) - [Security and Privacy Challenges of Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/das-2024-security-privacy-challenges-large-language/) - [Multilingual and Explainable Text Detoxification with Parallel Corpora](https://md.research.elamur.ai/free/en/papers/dementieva-2025-multilingual-explainable-text-detoxification-parallel/) - [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://md.research.elamur.ai/free/en/papers/deyoung-2020-eraser-benchmark-evaluate-rationalized-nlp/) - [Towards A Rigorous Science of Interpretable Machine Learning](https://md.research.elamur.ai/free/en/papers/doshi-2017-velez-towards-rigorous-science-interpretable-machine/) - [Bias and Fairness in Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/gallegos-2023-bias-fairness-large-language-models/) - [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://md.research.elamur.ai/free/en/papers/goyal-2016-making-v-vqa-matter-elevating/) - [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://md.research.elamur.ai/free/en/papers/han-2020-explaining-black-box-predictions-unveiling/) - [Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness?](https://md.research.elamur.ai/free/en/papers/jacovi-2020-faithfully-interpretable-nlp-systems-how/) - [Learning to Faithfully Rationalize by Construction](https://md.research.elamur.ai/free/en/papers/jain-2020-learning-faithfully-rationalize-construction/) - [WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-hop Inference](https://md.research.elamur.ai/free/en/papers/jansen-2018-worldtree-corpus-explanation-graphs-elementary/) - [Human Rationales as Attribution Priors for Explainable Stance Detection](https://md.research.elamur.ai/free/en/papers/jayaram-2021-human-rationales-as-attribution-priors/) - [Contextualizing Hate Speech Classifiers with Post-hoc Explanation](https://md.research.elamur.ai/free/en/papers/kennedy-2020-contextualizing-hate-speech-classifiers-post/) - [Understanding Black-box Predictions via Influence Functions](https://md.research.elamur.ai/free/en/papers/koh-2017-understanding-black-box-predictions-influence/) - [Explainable Automated Fact-Checking for Public Health Claims](https://md.research.elamur.ai/free/en/papers/kotonya-2020-explainable-automated-fact-checking-public/) - [大语言模型的幻觉问题研究综述](https://md.research.elamur.ai/free/en/papers/liu-2024-hallucinations-large-language/) - [Explainable Semantic Textual Similarity via Dissimilar Span Detection](https://md.research.elamur.ai/free/en/papers/lozano-2026-explainable-semantic-textual-similarity-dissimilar/) - [A Unified Approach to Interpreting Model Predictions](https://md.research.elamur.ai/free/en/papers/lundberg-2017-unified-approach-interpreting-model-predictions/) - [Faithful Chain-of-Thought Reasoning](https://md.research.elamur.ai/free/en/papers/lyu-2023-faithful-chain-thought-reasoning/) - [ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation](https://md.research.elamur.ai/free/en/papers/malik-2021-ildc-cjpe-indian-legal-documents/) - [Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persian](https://md.research.elamur.ai/free/en/papers/mehrazar-2026-can-llms-faithfully-explain-themselves/) - [Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models' Understanding of Discourse Relations](https://md.research.elamur.ai/free/en/papers/miao-2024-discursive-socratic-questioning-evaluating-faithfulness/) - [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://md.research.elamur.ai/free/en/papers/miller-2017-explanation-artificial-intelligence-insights-social/) - [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/min-2021-recent-advances-natural-language-processing/) - [Emojis as Anchors to Detect Arabic Offensive Language and Hate Speech](https://md.research.elamur.ai/free/en/papers/mubarak-2022-emojis-anchors-detect-arabic-offensive/) - [Explainable Prediction of Medical Codes from Clinical Text](https://md.research.elamur.ai/free/en/papers/mullenbach-2018-explainable-prediction-medical-codes-clinical/) - [SemEval-2021 Task 5: Toxic Spans Detection](https://md.research.elamur.ai/free/en/papers/pavlopoulos-2021-semeval-2021-task-5-toxic/) - [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://md.research.elamur.ai/free/en/papers/rei-2022-cometkiwi-ist-unbabel-2022-submission/) - [Explainable AI for Ethical Counter Speech Generation in Hate Speech Mitigation](https://md.research.elamur.ai/free/en/papers/ridoy-2026-explainable-ai-ethical-counter-speech/) - [ZIP: Quantifying Which Words Matter in Zero-Shot Instructional Prompts](https://md.research.elamur.ai/free/en/papers/sadr-2026-zip-quantifying-which-words-matter/) - [A Few Topical Tweets are Enough for Effective User Stance Detection](https://md.research.elamur.ai/free/en/papers/samih-2021-few-topical-tweets-are-enough/) - [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://md.research.elamur.ai/free/en/papers/sap-2020-social-bias-frames-reasoning-about/) - [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://md.research.elamur.ai/free/en/papers/selvaraju-2016-grad-cam-visual-explanations-deep/) - [Is Attention Interpretable?](https://md.research.elamur.ai/free/en/papers/serrano-2019-is-attention-interpretable/) - [Transparent Semantic Change Detection with Dependency-Based Profiles](https://md.research.elamur.ai/free/en/papers/tat-2026-transparent-semantic-change-detection-dependency/) - [Explore Political Discourse with Transformers. Emergent Paradigmatic and Syntagmatic Representations.](https://md.research.elamur.ai/free/en/papers/vanni-2026-explore-political-discourse-transformers-emergent/) - [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://md.research.elamur.ai/free/en/papers/wu-2021-polyjuice-generating-counterfactuals-explaining-evaluating/) - [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://md.research.elamur.ai/free/en/papers/ye-2022-unreliability-explanations-few-shot-prompting/) - [Findings of the WMT 2022 Shared Task on Quality Estimation](https://md.research.elamur.ai/free/en/papers/zerva-2022-findings-wmt-2022-shared-task/) - [Explainability for Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/zhao-2023-explainability-large-language-models-survey/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{ribeiro2016why, title = {{"Why Should I Trust You?": Explaining the Predictions of Any Classifier}}, author = {Ribeiro, Marco Tulio and Singh, Sameer and Guestrin, Carlos}, year = {2016}, doi = {10.48550/arxiv.1602.04938}, eprint = {1602.04938}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.1602.04938} } ``` - [next → A Character-level Decoder without Explicit Segmentation for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/chung-2016-character-level-decoder-without-explicit/) - [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/) ## References 29 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. S. Amershi, M. Chickering, S. M. Drucker, B. Lee, P. Simard, and J. Suh. Modeltracker: Redesigning performance analysis tools for machine learning. In Human Factors in Computing Systems (CHI), 2015. [find](https://scholar.google.com/scholar?q=S%2E+Amershi%2C+M%2E+Chickering%2C+S%2E+M%2E+Drucker%2C+B%2E+Lee%2C+P%2E+Simard%2C+and+J%2E+Suh%2E+Modeltracker%3A+Redesigning+performance+analysis+tools+for+machine+learning%2E+In+Human+Factors+in+Computing+Systems+%28CHI%29%2C+2015%2E) 2. D. Baehrens, T. Schroeter, S. Harmeling, M. Kawanabe, K. Hansen, and K.-R. Müller. How to explain individual classification decisions. Journal of Machine Learning Research, 11, 2010. [find](https://scholar.google.com/scholar?q=D%2E+Baehrens%2C+T%2E+Schroeter%2C+S%2E+Harmeling%2C+M%2E+Kawanabe%2C+K%2E+Hansen%2C+and+K%2E%2DR%2E+Mu%CC%88ller%2E+How+to+explain+individual+classification+decisions%2E+Journal+of+Machine+Learning+Research%2C+11%2C+2010%2E) 3. A. Bansal, A. Farhadi, and D. Parikh. Towards transparent systems: Semantic characterization of failure modes. In European Conference on Computer Vision (ECCV), 2014. [find](https://scholar.google.com/scholar?q=A%2E+Bansal%2C+A%2E+Farhadi%2C+and+D%2E+Parikh%2E+Towards+transparent+systems%3A+Semantic+characterization+of+failure+modes%2E+In+European+Conference+on+Computer+Vision+%28ECCV%29%2C+2014%2E) 4. J. Blitzer, M. Dredze, and F. Pereira. Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. In Association for Computational Linguistics (ACL), 2007. [find](https://scholar.google.com/scholar?q=J%2E+Blitzer%2C+M%2E+Dredze%2C+and+F%2E+Pereira%2E+Biographies%2C+bollywood%2C+boom%2Dboxes+and+blenders%3A+Domain+adaptation+for+sentiment+classification%2E+In+Association+for+Computational+Linguistics+%28ACL%29%2C+2007%2E) [our card](https://md.research.elamur.ai/free/en/papers/blitzer-2007-biographies-bollywood-boom-boxes-blenders/) 5. J. Q. Candela, M. Sugiyama, A. Schwaighofer, and N. D. Lawrence. Dataset Shift in Machine Learning. MIT, 2009. [find](https://scholar.google.com/scholar?q=J%2E+Q%2E+Candela%2C+M%2E+Sugiyama%2C+A%2E+Schwaighofer%2C+and+N%2E+D%2E+Lawrence%2E+Dataset+Shift+in+Machine+Learning%2E+MIT%2C+2009%2E) 6. R. Caruana, Y. Lou, J. Gehrke, P. Koch, M. Sturm, and N. Elhadad. Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. In Knowledge Discovery and Data Mining (KDD), 2015. [find](https://scholar.google.com/scholar?q=R%2E+Caruana%2C+Y%2E+Lou%2C+J%2E+Gehrke%2C+P%2E+Koch%2C+M%2E+Sturm%2C+and+N%2E+Elhadad%2E+Intelligible+models+for+healthcare%3A+Predicting+pneumonia+risk+and+hospital+30%2Dday+readmission%2E+In+Knowledge+Discovery+and+Data+Mining+) 7. M. W. Craven and J. W. Shavlik. Extracting tree-structured representations of trained networks. Neural information processing systems (NIPS), pages 24–30, 1996. [find](https://scholar.google.com/scholar?q=M%2E+W%2E+Craven+and+J%2E+W%2E+Shavlik%2E+Extracting+tree%2Dstructured+representations+of+trained+networks%2E+Neural+information+processing+systems+%28NIPS%29%2C+pages+24%E2%80%9330%2C+1996%2E) 8. M. T. Dzindolet, S. A. Peterson, R. A. Pomranky, L. G. Pierce, and H. P. Beck. The role of trust in automation reliance. Int. J. Hum.-Comput. Stud., 58(6), 2003. [find](https://scholar.google.com/scholar?q=M%2E+T%2E+Dzindolet%2C+S%2E+A%2E+Peterson%2C+R%2E+A%2E+Pomranky%2C+L%2E+G%2E+Pierce%2C+and+H%2E+P%2E+Beck%2E+The+role+of+trust+in+automation+reliance%2E+Int%2E+J%2E+Hum%2E%2DComput%2E+Stud%2E%2C+58%286%29%2C+2003%2E) 9. B. Efron, T. Hastie, I. Johnstone, and R. Tibshirani. Least angle regression. Annals of Statistics, 32:407–499, 2004. [find](https://scholar.google.com/scholar?q=B%2E+Efron%2C+T%2E+Hastie%2C+I%2E+Johnstone%2C+and+R%2E+Tibshirani%2E+Least+angle+regression%2E+Annals+of+Statistics%2C+32%3A407%E2%80%93499%2C+2004%2E) 10. U. Feige. A threshold of ln n for approximating set cover. J. ACM, 45(4), July 1998. [find](https://scholar.google.com/scholar?q=U%2E+Feige%2E+A+threshold+of+ln+n+for+approximating+set+cover%2E+J%2E+ACM%2C+45%284%29%2C+July+1998%2E) 11. A. Groce, T. Kulesza, C. Zhang, S. Shamasunder, M. Burnett, W.-K. Wong, S. Stumpf, S. Das, A. Shinsel, F. Bice, and K. McIntosh. You are the only possible oracle: Effective test selection for end users of interactive machine learning systems. IEEE Trans. Softw. Eng., 40(3), 2014. [find](https://scholar.google.com/scholar?q=A%2E+Groce%2C+T%2E+Kulesza%2C+C%2E+Zhang%2C+S%2E+Shamasunder%2C+M%2E+Burnett%2C+W%2E%2DK%2E+Wong%2C+S%2E+Stumpf%2C+S%2E+Das%2C+A%2E+Shinsel%2C+F%2E+Bice%2C+and+K%2E+McIntosh%2E+You+are+the+only+possible+oracle%3A+Effective+test+selection+for+end+user) 12. J. L. Herlocker, J. A. Konstan, and J. Riedl. Explaining collaborative filtering recommendations. In Conference on Computer Supported Cooperative Work (CSCW), 2000. [find](https://scholar.google.com/scholar?q=J%2E+L%2E+Herlocker%2C+J%2E+A%2E+Konstan%2C+and+J%2E+Riedl%2E+Explaining+collaborative+filtering+recommendations%2E+In+Conference+on+Computer+Supported+Cooperative+Work+%28CSCW%29%2C+2000%2E) 13. A. Karpathy and F. Li. Deep visual-semantic alignments for generating image descriptions. In Computer Vision and Pattern Recognition (CVPR), 2015. [find](https://scholar.google.com/scholar?q=A%2E+Karpathy+and+F%2E+Li%2E+Deep+visual%2Dsemantic+alignments+for+generating+image+descriptions%2E+In+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+2015%2E) [our card](https://md.research.elamur.ai/free/en/papers/karpathy-2014-deep-visual-semantic-alignments-generating/) 14. S. Kaufman, S. Rosset, and C. Perlich. Leakage in data mining: Formulation, detection, and avoidance. In Knowledge Discovery and Data Mining (KDD), 2011. [find](https://scholar.google.com/scholar?q=S%2E+Kaufman%2C+S%2E+Rosset%2C+and+C%2E+Perlich%2E+Leakage+in+data+mining%3A+Formulation%2C+detection%2C+and+avoidance%2E+In+Knowledge+Discovery+and+Data+Mining+%28KDD%29%2C+2011%2E) 15. A. Krause and D. Golovin. Submodular function maximization. In Tractability: Practical Approaches to Hard Problems. Cambridge University Press, February 2014. [find](https://scholar.google.com/scholar?q=A%2E+Krause+and+D%2E+Golovin%2E+Submodular+function+maximization%2E+In+Tractability%3A+Practical+Approaches+to+Hard+Problems%2E+Cambridge+University+Press%2C+February+2014%2E) 16. T. Kulesza, M. Burnett, W.-K. Wong, and S. Stumpf. Principles of explanatory debugging to personalize interactive machine learning. In Intelligent User Interfaces (IUI), 2015. [find](https://scholar.google.com/scholar?q=T%2E+Kulesza%2C+M%2E+Burnett%2C+W%2E%2DK%2E+Wong%2C+and+S%2E+Stumpf%2E+Principles+of+explanatory+debugging+to+personalize+interactive+machine+learning%2E+In+Intelligent+User+Interfaces+%28IUI%29%2C+2015%2E) 17. B. Letham, C. Rudin, T. H. McCormick, and D. Madigan. Interpretable classifiers using rules and bayesian analysis: Building a better stroke prediction model. Annals of Applied Statistics, 2015. [find](https://scholar.google.com/scholar?q=B%2E+Letham%2C+C%2E+Rudin%2C+T%2E+H%2E+McCormick%2C+and+D%2E+Madigan%2E+Interpretable+classifiers+using+rules+and+bayesian+analysis%3A+Building+a+better+stroke+prediction+model%2E+Annals+of+Applied+Statistics%2C+2015%2E) 18. D. Martens and F. Provost. Explaining data-driven document classifications. MIS Q., 38(1), 2014. [find](https://scholar.google.com/scholar?q=D%2E+Martens+and+F%2E+Provost%2E+Explaining+data%2Ddriven+document+classifications%2E+MIS+Q%2E%2C+38%281%29%2C+2014%2E) 19. T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. Distributed representations of words and phrases and their compositionality. In Neural Information Processing Systems (NIPS). 2013. [find](https://scholar.google.com/scholar?q=T%2E+Mikolov%2C+I%2E+Sutskever%2C+K%2E+Chen%2C+G%2E+S%2E+Corrado%2C+and+J%2E+Dean%2E+Distributed+representations+of+words+and+phrases+and+their+compositionality%2E+In+Neural+Information+Processing+Systems+%28NIPS%29%2E+2013%2E) 20. K. Patel, J. Fogarty, J. A. Landay, and B. Harrison. Investigating statistical machine learning as a tool for software development. In Human Factors in Computing Systems (CHI), 2008. [find](https://scholar.google.com/scholar?q=K%2E+Patel%2C+J%2E+Fogarty%2C+J%2E+A%2E+Landay%2C+and+B%2E+Harrison%2E+Investigating+statistical+machine+learning+as+a+tool+for+software+development%2E+In+Human+Factors+in+Computing+Systems+%28CHI%29%2C+2008%2E) 21. K. Patel, N. Bancroft, S. M. Drucker, J. Fogarty, A. J. Ko, and J. Landay. Gestalt: Integrated support for implementation and analysis in machine learning. In User Interface Software and Technology (UIST), 2010. [find](https://scholar.google.com/scholar?q=K%2E+Patel%2C+N%2E+Bancroft%2C+S%2E+M%2E+Drucker%2C+J%2E+Fogarty%2C+A%2E+J%2E+Ko%2C+and+J%2E+Landay%2E+Gestalt%3A+Integrated+support+for+implementation+and+analysis+in+machine+learning%2E+In+User+Interface+Software+and+Technology+%28U) 22. I. Sanchez, T. Rocktaschel, S. Riedel, and S. Singh. Towards extracting faithful and descriptive representations of latent variable models. In AAAI Spring Syposium on Knowledge Representation and Reasoning (KRR): Integrating Symbolic and Neural Approaches, 2015. [find](https://scholar.google.com/scholar?q=I%2E+Sanchez%2C+T%2E+Rocktaschel%2C+S%2E+Riedel%2C+and+S%2E+Singh%2E+Towards+extracting+faithful+and+descriptive+representations+of+latent+variable+models%2E+In+AAAI+Spring+Syposium+on+Knowledge+Representation+and+Reas) 23. D. Sculley, G. Holt, D. Golovin, E. Davydov, T. Phillips, D. Ebner, V. Chaudhary, M. Young, and J.-F. Crespo. Hidden technical debt in machine learning systems. In Neural Information Processing Systems (NIPS). 2015. [find](https://scholar.google.com/scholar?q=D%2E+Sculley%2C+G%2E+Holt%2C+D%2E+Golovin%2C+E%2E+Davydov%2C+T%2E+Phillips%2C+D%2E+Ebner%2C+V%2E+Chaudhary%2C+M%2E+Young%2C+and+J%2E%2DF%2E+Crespo%2E+Hidden+technical+debt+in+machine+learning+systems%2E+In+Neural+Information+Processing+System) 24. E. Strumbelj and I. Kononenko. An efficient explanation of individual classifications using game theory. Journal of Machine Learning Research, 11, 2010. [find](https://scholar.google.com/scholar?q=E%2E+Strumbelj+and+I%2E+Kononenko%2E+An+efficient+explanation+of+individual+classifications+using+game+theory%2E+Journal+of+Machine+Learning+Research%2C+11%2C+2010%2E) 25. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In Computer Vision and Pattern Recognition (CVPR), 2015. [find](https://scholar.google.com/scholar?q=C%2E+Szegedy%2C+W%2E+Liu%2C+Y%2E+Jia%2C+P%2E+Sermanet%2C+S%2E+Reed%2C+D%2E+Anguelov%2C+D%2E+Erhan%2C+V%2E+Vanhoucke%2C+and+A%2E+Rabinovich%2E+Going+deeper+with+convolutions%2E+In+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+2015%2E) 26. B. Ustun and C. Rudin. Supersparse linear integer models for optimized medical scoring systems. Machine Learning, 2015. [find](https://scholar.google.com/scholar?q=B%2E+Ustun+and+C%2E+Rudin%2E+Supersparse+linear+integer+models+for+optimized+medical+scoring+systems%2E+Machine+Learning%2C+2015%2E) 27. F. Wang and C. Rudin. Falling rule lists. In Artificial Intelligence and Statistics (AISTATS), 2015. [find](https://scholar.google.com/scholar?q=F%2E+Wang+and+C%2E+Rudin%2E+Falling+rule+lists%2E+In+Artificial+Intelligence+and+Statistics+%28AISTATS%29%2C+2015%2E) 28. K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhutdinov, R. Zemel, and Y. Bengio. Show, attend and tell: Neural image caption generation with visual attention. In International Conference on Machine Learning (ICML), 2015. [find](https://scholar.google.com/scholar?q=K%2E+Xu%2C+J%2E+Ba%2C+R%2E+Kiros%2C+K%2E+Cho%2C+A%2E+Courville%2C+R%2E+Salakhutdinov%2C+R%2E+Zemel%2C+and+Y%2E+Bengio%2E+Show%2C+attend+and+tell%3A+Neural+image+caption+generation+with+visual+attention%2E+In+International+Conference+on+Ma) [our card](https://md.research.elamur.ai/free/en/papers/xu-2015-show-attend-tell-neural-image/) 29. P. Zhang, J. Wang, A. Farhadi, M. Hebert, and D. Parikh. Predicting failures of vision systems. In Computer Vision and Pattern Recognition (CVPR), 2014. [find](https://scholar.google.com/scholar?q=P%2E+Zhang%2C+J%2E+Wang%2C+A%2E+Farhadi%2C+M%2E+Hebert%2C+and+D%2E+Parikh%2E+Predicting+failures+of+vision+systems%2E+In+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+2014%2E)