{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T04:25:28Z","timestamp":1785558328278,"version":"3.56.0"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T00:00:00Z","timestamp":1690416000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T00:00:00Z","timestamp":1690416000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2040989"],"award-info":[{"award-number":["IIS-2040989"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2046873"],"award-info":[{"award-number":["IIS-2046873"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2008956"],"award-info":[{"award-number":["IIS-2008956"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2008461"],"award-info":[{"award-number":["IIS-2008461"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2040989"],"award-info":[{"award-number":["IIS-2040989"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2008461"],"award-info":[{"award-number":["IIS-2008461"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2040989"],"award-info":[{"award-number":["IIS-2040989"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2040989"],"award-info":[{"award-number":["IIS-2040989"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2046873"],"award-info":[{"award-number":["IIS-2046873"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2008956"],"award-info":[{"award-number":["IIS-2008956"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"name":"I was supported by a fellowship from the hasso plattner institute during the bulk of completing this work."},{"name":"Google, JP Morgan, Amazon, Harvard Data Science Initiative, D^3 institute at Harvard"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Practitioners increasingly use machine learning (ML) models, yet models have become more complex and harder to understand. To understand complex models, researchers have proposed techniques to explain model predictions. However, practitioners struggle to use explainability methods because they do not know which explanation to choose and how to interpret the explanation. Here we address the challenge of using explainability methods by proposing TalkToModel: an interactive dialogue system that explains ML models through natural language conversations. TalkToModel consists of three components: an adaptive dialogue engine that interprets natural language and generates meaningful responses; an execution component that constructs the explanations used in the conversation; and a conversational interface. In real-world evaluations, 73% of healthcare workers agreed they would use TalkToModel over existing systems for understanding a disease prediction model, and 85% of ML professionals agreed TalkToModel was easier to use, demonstrating that TalkToModel is highly effective for model explainability.<\/jats:p>","DOI":"10.1038\/s42256-023-00692-8","type":"journal-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T12:02:40Z","timestamp":1690459360000},"page":"873-883","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":94,"title":["Explaining machine learning models with interactive natural language conversations using TalkToModel"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4186-2937","authenticated-orcid":false,"given":"Dylan","family":"Slack","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5324-5824","authenticated-orcid":false,"given":"Satyapriya","family":"Krishna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Himabindu","family":"Lakkaraju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sameer","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,27]]},"reference":[{"key":"692_CR1","doi-asserted-by":"crossref","unstructured":"Lakkaraju, H., Bach, S. H. & Leskovec, J. Interpretable decision sets: a joint framework for description and prediction. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 1675\u20131684 (Association for Computing Machinery, 2016).","DOI":"10.1145\/2939672.2939874"},{"key":"692_CR2","doi-asserted-by":"crossref","unstructured":"Angelino, E., Larus-Stone, N., Alabi, D., Seltzer, M. & Rudin, C. Learning certifiably optimal rule lists. In Proc. 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 35\u201344 (Association for Computing Machinery, 2017).","DOI":"10.1145\/3097983.3098047"},{"key":"692_CR3","doi-asserted-by":"crossref","unstructured":"Lou, Y., Caruana, R., Gehrke, J. & Hooker, G. Accurate intelligible models with pairwise interactions. In Proc. 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (eds Ghani, R. et al.) 623\u2013631 (Association for Computing Machinery, 2013).","DOI":"10.1145\/2487575.2487579"},{"key":"692_CR4","unstructured":"Agarwal, R. et al. Neural additive models: interpretable machine learning with neural nets. Adv. Neural Inf. Process. Syst. 34, 4699\u20134711 (2021)."},{"key":"692_CR5","unstructured":"Chang, C.-H., Caruana, R. & Goldenberg, A. Node-GAM: neural generalized additive model for interpretable deep learning. In International Conference on Learning Representations (2022)."},{"key":"692_CR6","unstructured":"Ribeiro, M. T., Singh, S. & Guestrin, C. Model-agnostic interpretability of machine learning. In ICML Workshop on Human Interpretability in Machine Learning (2016)."},{"key":"692_CR7","unstructured":"Slack, D., Hilgard, A., Singh, S. & Lakkaraju, H. Reliable post hoc explanations: modeling uncertainty in explainability. Adv. Neural Inf. Process. Syst. 34, 9391\u20139404 (2021)."},{"key":"692_CR8","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision 618\u2013626 (IEEE, 2017).","DOI":"10.1109\/ICCV.2017.74"},{"key":"692_CR9","unstructured":"Slack, D., Rauschmayr, N. & Kenthapadi, K. Defuse: training more robust models through creation and correction of novel model errors. In NeurIPS 2021 Workshop on Explainable AI Approaches for Debugging and Diagnosis (2021)."},{"key":"692_CR10","unstructured":"Hase, P., Xie, H. & Bansal, M. The out-of-distribution problem in explainability and search methods for feature importance explanations. Adv. Neural Inf. Process. Syst. 34, 3650\u20133666 (2021)."},{"key":"692_CR11","unstructured":"Simonyan, K., Vedaldi, A. & Zisserman, A. Deep inside convolutional networks: visualising image classification models and saliency maps. In Workshop at International Conference on Learning Representations (2014)."},{"key":"692_CR12","unstructured":"Lakkaraju, H., Slack, D., Chen, Y., Tan, C. & Sing, S. Rethinkingexplainability as a dialogue: a practitioner\u2019s perspective. HAI Workshop @ NeurIPS (2022)."},{"key":"692_CR13","doi-asserted-by":"crossref","unstructured":"Kaur, H. et al. Interpreting interpretability: understanding data scientists\u2019 use of interpretability tools for machine learning. In Proc. 2020 CHI Conference on Human Factors in Computing Systems 1\u201314 (Association for Computing Machinery, 2020).","DOI":"10.1145\/3313831.3376219"},{"key":"692_CR14","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1145\/3282486","volume":"62","author":"DS Weld","year":"2019","unstructured":"Weld, D. S. & Bansal, G. The challenge of crafting intelligible intelligence. Commun. ACM 62, 70\u201379 (2019).","journal-title":"Commun. ACM"},{"key":"692_CR15","unstructured":"Fok, R. & Weld, D. S. In search of verifiability: explanations rarely enable complementary performance in AI-advised decision making. Preprint at https:\/\/arxiv.org\/abs\/2305.07722 (2023)."},{"key":"692_CR16","doi-asserted-by":"crossref","unstructured":"Tenney, I. et al. The language interpretability tool: extensible, interactive visualizations and analysis for NLP models. In Proc. 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (eds Liu, Q. & Schlangen, D.) 107\u2013118 (Association for Computational Linguistics, 2020).","DOI":"10.18653\/v1\/2020.emnlp-demos.15"},{"key":"692_CR17","unstructured":"Wexler, J. et al. The what-if tool: interactive probing of machine learning models. IEEE Trans. Vis. Comput. Graph. 26, 56\u201365 (2020)."},{"key":"692_CR18","unstructured":"Ward, N. G. & DeVault, D. Ten challenges in highly-interactive dialog systems. In AAAI Conference on Artificial Intelligence (2015)."},{"key":"692_CR19","unstructured":"Carenini, G., Mittal, V. O. & Moore, J. D. Generating patient-specific interactive natural language explanations. In Proc. Annual Symposium on Computer Applications in Medical Care 5\u20139 (1994)."},{"key":"692_CR20","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1146\/annurev.psych.54.101601.145041","volume":"54","author":"JW Pennebaker","year":"2002","unstructured":"Pennebaker, J. W., Mehl, M. R. & Niederhoffer, K. G. Psychological aspects of natural language use: our words, our selves. Annu. Rev. Psychol. 54, 547\u2013577 (2002).","journal-title":"Annu. Rev. Psychol."},{"key":"692_CR21","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1007\/s11431-020-1692-3","volume":"63","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Takanobu, R., Zhu, Q., Huang, M. & Zhu, X. Recent advances and challenges in task-oriented dialog systems. Sci. China Technol. Sci. 63, 2011\u20132027 (2020).","journal-title":"Sci. China Technol. Sci."},{"key":"692_CR22","doi-asserted-by":"crossref","unstructured":"Sokol, K. & Flach, P. Glass-box: explaining AI decisions with counterfactual statements through conversation with a voice-enabled virtual assistant. In Proc. 27th International Joint Conference on Artificial Intelligence (ed. Lang, J.) 5868\u20135870 (IJCAI, 2018).","DOI":"10.24963\/ijcai.2018\/865"},{"key":"692_CR23","unstructured":"Feldhus, N., Ravichandran, A. M. & M\u00f6ller, S. Mediators: conversational agents explaining NLP model behavior. IJCAI-ECAI Workshop on Explainable Artificial Intelligence (XAI) (2022)."},{"key":"692_CR24","unstructured":"Sutskever, I., Vinyals, O. & Le, Q. V. Sequence to sequence learning with neural networks. In Proc. 27th International Conference on Neural Information Processing Systems Vol. 2 (eds Ghahramani, Z. et al.) 3104\u20133112 (MIT Press, 2014)."},{"key":"692_CR25","doi-asserted-by":"crossref","unstructured":"Yu, T. et al. Spider: a large-scale human-labeled dataset for omplex and cross-domain semantic parsing and text-to-SQL task. In Proc. 2018 Conference on Empirical Methods in Natural Language Processing (eds Riloff, E. et al.) 3911\u20133921 (Association for Computational Linguistics, 2018).","DOI":"10.18653\/v1\/D18-1425"},{"key":"692_CR26","unstructured":"Dua, D. & Graff, C. UCI Machine Learning Repository (UCI, 2017); http:\/\/archive.ics.uci.edu\/ml"},{"key":"692_CR27","unstructured":"Angwin, J., Larson, J., Mattu, S. & Kirchner, L. Machine bias. ProPublica (2016)."},{"key":"692_CR28","unstructured":"Wang, B. & Komatsuzaki, A. GPT-J-6B: a 6 billion parameter autoregressive language model. GitHub https:\/\/github.com\/kingoflolz\/mesh-transformer-jax (2021)."},{"key":"692_CR29","unstructured":"Brown, T. et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877\u20131901 (2020)."},{"key":"692_CR30","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C. et al. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 5485\u20135551 (2020).","journal-title":"J. Mach. Learn. Res."},{"key":"692_CR31","doi-asserted-by":"crossref","unstructured":"Min, S. et al. Rethinking the role of demonstrations: what makes in-context learning work? In Proc. 2022 Conference on Empirical Methods in Natural Language Processing 11048\u201311064 (Association for Computational Linguistics, 2022).","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"692_CR32","unstructured":"Xie, S. M., Raghunathan, A., Liang, P. & Ma, T. An explanation of in-context learning as implicit bayesian inference. In International Conference on Learning Representations (2022)."},{"key":"692_CR33","doi-asserted-by":"crossref","unstructured":"Reimers, N. & Gurevych, I. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proc. 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (eds Pad\u00f3, S. & Huang, R) 3982\u20133992 (Association for Computational Linguistics, 2019).","DOI":"10.18653\/v1\/D19-1410"},{"key":"692_CR34","doi-asserted-by":"crossref","unstructured":"Shin, R. et al. Constrained language models yield few-shot semantic parsers. In Proc. 2021 Conference on Empirical Methods in Natural Language Processing (eds Moens, M.-F. et al.) 7699\u20137715 (Association for Computational Linguistics, 2021).","DOI":"10.18653\/v1\/2021.emnlp-main.608"},{"key":"692_CR35","doi-asserted-by":"crossref","unstructured":"Talmor, A., Geva, M. & Berant, J. Evaluating semantic parsing against a simple web-based question answering model. In Proc. 6th Joint Conference on Lexical and Computational Semantics (eds Ide, N. et al.) 161\u2013167 (Association for Computational Linguistics, 2017).","DOI":"10.18653\/v1\/S17-1020"},{"key":"692_CR36","doi-asserted-by":"crossref","unstructured":"Gupta, S., Singh, S. & Gardner, M. Structurally diverse sampling for sample-efficient training and comprehensive evaluation. In Findings of the Association for Computational Linguistics: EMNLP 2022 (eds Goldberg, Y. et al.) 4966\u20134979 (Association for Computational Linguistics, 2022).","DOI":"10.18653\/v1\/2022.findings-emnlp.365"},{"key":"692_CR37","doi-asserted-by":"crossref","unstructured":"Oren, I., Herzig, J., Gupta, N., Gardner, M. & Berant, J. Improving compositional generalization in semantic parsing. In Findings of the Association for Computational Linguistics: EMNLP 2020 (eds Cohn, T. et al.) 2482\u20132495 (Association for Computational Linguistics, 2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.225"},{"key":"692_CR38","doi-asserted-by":"crossref","unstructured":"Yin, P. et al. Compositional generalization for neural semantic parsing via span-level supervised attention. In Proc. 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (eds Toutanova, K. et al.) 2810\u20132823 (Association for Computational Linguistics, 2021).","DOI":"10.18653\/v1\/2021.naacl-main.225"},{"key":"692_CR39","doi-asserted-by":"publisher","unstructured":"Dijk, O. et al. oegedijk\/explainerdashboard: v0.3.8.2: reverses set_shap_values bug introduced in 0.3.8.1. Zenodo https:\/\/doi.org\/10.5281\/zenodo.6408776 (2022).","DOI":"10.5281\/zenodo.6408776"},{"key":"692_CR40","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"692_CR41","doi-asserted-by":"crossref","unstructured":"Chen, Q., Schnabel, T., Nushi, B. & Amershi, S. Hint: integration testing for AI-based features with humans in the loop. In 27th International Conference on Intelligent User Interfaces 549\u2013565 (ACM, 2022).","DOI":"10.1145\/3490099.3511141"},{"key":"692_CR42","unstructured":"Freed, M. et al. RADAR: a personal assistant that learns to reduce email overload. In Proc. 23rd National Conference on Artificial Intelligence Vol. 3 (ed. Cohn, A.) 1287\u20131293 (AAAI Press, 2008)."},{"key":"692_CR43","doi-asserted-by":"crossref","unstructured":"Glass, A., McGuinness, D. L. & Wolverton, M. Toward establishing trust in adaptive agents. In Proc. 13th International Conference on Intelligent User Interfaces 227\u2013236 (Association for Computing Machinery, 2008).","DOI":"10.1145\/1378773.1378804"},{"key":"692_CR44","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.jbef.2017.12.004","volume":"17","author":"S Palan","year":"2018","unstructured":"Palan, S. & Schitter, C. Prolific.ac\u2014a subject pool for online experiments. J. Behav. Exp. Finance 17, 22\u201327 (2018).","journal-title":"J. Behav. Exp. Finance"},{"key":"692_CR45","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1145\/3166054.3166058","volume":"19","author":"H Chen","year":"2017","unstructured":"Chen, H., Liu, X., Yin, D. & Tang, J. A survey on dialogue systems: recent advances and new frontiers. SIGKDD Explor. Newsl. 19, 25\u201335 (2017).","journal-title":"SIGKDD Explor. Newsl."},{"key":"692_CR46","unstructured":"Li, X., Chen, Y.-N., Li, L., Gao, J. & Celikyilmaz, A. End-to-end task-completion neural dialogue systems. In Proc. Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (eds Kondrak, G. & Watanabe, T.) 733\u2013743 (2017)."},{"key":"692_CR47","doi-asserted-by":"crossref","unstructured":"Dong, C. et al. A survey of natural language generation. ACM Comput. Surv. 55, 1\u201338 (2022).","DOI":"10.1145\/3554727"},{"key":"692_CR48","doi-asserted-by":"crossref","unstructured":"Liu, Y., Han, K., Tan, Z. & Lei, Y. Using context information for dialog act classification in DNN framework. In Proc. 2017 Conference on Empirical Methods in Natural Language Processing (eds Palmer, M. et al.) 2170\u20132178 (Association for Computational Linguistics, 2017).","DOI":"10.18653\/v1\/D17-1231"},{"key":"692_CR49","doi-asserted-by":"crossref","unstructured":"Cai, W. & Chen, L. Predicting user intents and satisfaction with dialogue-based conversational recommendations. In Proc. 28th ACM Conference on User Modeling, Adaptation and Personalization (eds Kuflik, T. et al.) 33\u201342 (Association for Computing Machinery, 2020).","DOI":"10.1145\/3340631.3394856"},{"key":"692_CR50","doi-asserted-by":"crossref","unstructured":"Liao, Q. V., Gruen, D. & Miller, S. Questioning the AI: informing design practices for explainable AI user experiences. In Proc. 2020 CHI Conference on Human Factors in Computing Systems 1\u201315 (Association for Computing Machinery, 2020).","DOI":"10.1145\/3313831.3376590"},{"key":"692_CR51","doi-asserted-by":"crossref","unstructured":"Grosz, B. J., Joshi, A. K. & Weinstein, S. Providing a unified account of definite noun phrases in discourse. In 21st Annual Meeting of the Association for Computational Linguistics 44\u201350 (Association for Computational Linguistics, 1983).","DOI":"10.3115\/981311.981320"},{"key":"692_CR52","doi-asserted-by":"crossref","unstructured":"Tseng, B.-H. et al. CREAD: combined resolution of ellipses and anaphora in dialogues. In Proc. 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (eds Toutanova, K. et al.) 3390\u20133406 (Association for Computational Linguistics, 2021).","DOI":"10.18653\/v1\/2021.naacl-main.265"},{"key":"692_CR53","unstructured":"Guo, D., Tang, D., Duan, N., Zhou, M. & Yin, J. Dialog-to-action: conversational question answering over a large-scale knowledge base. In Proc. 32nd International Conference on Neural Information Processing Systems (eds Bengio, S. et al.) 2946\u20132955 (Curran Associates Inc., 2018)."},{"key":"692_CR54","doi-asserted-by":"crossref","unstructured":"Gao, S., Sethi, A., Agarwal, S., Chung, T. & Hakkani-Tur, D. Dialog state tracking: s neural reading comprehension approach. In Proc. 20th Annual SIGdial Meeting on Discourse and Dialogue (eds Nakamura, S. et al.) 264\u2013273 (Association for Computational Linguistics, 2019).","DOI":"10.18653\/v1\/W19-5932"},{"key":"692_CR55","doi-asserted-by":"crossref","unstructured":"Gao, J., Galley, M. & Li, L. Neural approaches to conversational AI. In Proc. 56th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts (eds Artzi, Y. & Eisenstein, J.) 2\u20137 (Association for Computational Linguistics, 2018).","DOI":"10.18653\/v1\/P18-5002"},{"key":"692_CR56","doi-asserted-by":"crossref","unstructured":"Rieser, V. & Lemon, O. in Data-Driven Methods for Adaptive Spoken Dialogue Systems (eds Lemon, O. & Pietquin, O.) 5\u201317 (Springer, 2012).","DOI":"10.1007\/978-1-4614-4803-7_2"},{"key":"692_CR57","unstructured":"Zhao, Z., Wallace, E., Feng, S., Klein, D. & Singh, S. Calibrate before use: improving few-shot performance of language models. In Proc. 38th International Conference on Machine Learning (eds Meila, M. & Zhang, T.) 12697-12706 (PMLR, 2021)."},{"key":"692_CR58","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. In International Conference on Learning Representations (2019)."},{"key":"692_CR59","doi-asserted-by":"crossref","unstructured":"Shao, Y. et al. Generating high-quality and informative conversation responses with sequence-to-equence models. In Proc. 2017 Conference on Empirical Methods in Natural Language Processing (eds Palmer, M. et al.) 2210\u20132219 (Association for Computational Linguistics, 2017).","DOI":"10.18653\/v1\/D17-1235"},{"key":"692_CR60","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F. & Wattenberg, M. Smoothgrad: removing noise by adding noise. In Workshop on Visualization for Deep Learning (2017)."},{"key":"692_CR61","unstructured":"Yeh, C.-K., Hsieh, C.-Y., Suggala, A., Inouye, D., & Ravikumar, P. On the (In)fidelity and sensitivity of explanations. In Proc. 33rd International Conference on Neural Information Processing Systems (eds Wallach, H. M. et al.) 10967\u201310978 (Curran Associates, Inc. 2019)."},{"key":"692_CR62","unstructured":"Chen, J., Song, L., Wainwright, M. J. & Jordan, M. I. L-Shapley and c-Shapley: efficient model interpretation for structured data. In International Conference on Learning Representations (2019)."},{"key":"692_CR63","unstructured":"Agarwal, S. et al. Towards the unification and robustness of perturbation and gradient-based explanations. In Proc. 38th International Conference on Machine Learning (eds Meila, M. & Zhang, T.) 110\u2013119 (PMLR, 2021)."},{"key":"692_CR64","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. T., Singh, S. & Guestrin, C. 2016. \"Why should I trust you?\": explaining the predictions of any classifier. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 1135\u20131144 (Association for Computing Machinery, 2016).","DOI":"10.1145\/2939672.2939778"},{"key":"692_CR65","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2, 56\u201367 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"692_CR66","doi-asserted-by":"crossref","unstructured":"Lakkaraju, H., Kamar, E., Caruana, R. & Leskovec, J. Faithful and customizable explanations of black box models. In Proc. 2019 AAAI\/ACM Conference on AI, Ethics, and Society 131\u2013138 (Association for Computing Machinery, 2019).","DOI":"10.1145\/3306618.3314229"},{"key":"692_CR67","unstructured":"Plumb, G., Molitor, D. & Talwalkar, A. Model agnostic supervised local explanations. In Proc. 32nd International Conference on Neural Information Processing Systems (eds Bengio, S. et al.) 2520\u20132529 (Curran Associates, 2018)."},{"key":"692_CR68","unstructured":"Li, J., Nagarajan, V., Plumb, G. & Talwalkar, A. A learning theoretic perspective on local explainability. In International Conference on Learning Representations (2020)."},{"key":"692_CR69","doi-asserted-by":"publisher","first-page":"22071","DOI":"10.1073\/pnas.1900654116","volume":"116","author":"WJ Murdoch","year":"2019","unstructured":"Murdoch, W. J., Singh, C., Kumbier, K., Abbasi-Asl, R. & Yu, B. Definitions, methods, and applications in interpretable machine learning. Proc. Natl Acad. Sci. USA 116, 22071\u201322080 (2019).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"692_CR70","unstructured":"Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In Proc. 34th International Conference on Machine Learning Vol. 70 (eds Precup, D. & Teh, Y. W.) 3319\u20133328 (JMLR.org, 2017)."},{"key":"692_CR71","doi-asserted-by":"crossref","unstructured":"Krishna, S. et al. The disagreement problem in explainable machine learning: a practitioner\u2019s perspective. ICML Workshop on Interpretable Machine Learning in Healthcare (2022).","DOI":"10.21203\/rs.3.rs-2963888\/v1"},{"key":"692_CR72","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-11012-2","volume":"12","author":"C Meng","year":"2022","unstructured":"Meng, C., Trinh, L., Xu, N., Enouen, J. & Liu, Y. Interpretability and fairness evaluation of deep learning models on MIMIC-IV dataset. Sci. Rep. 12, 7166 (2022).","journal-title":"Sci. Rep."},{"key":"692_CR73","unstructured":"Hooker, S., Erhan, D., Kindermans, P.-J. & Kim, B. A Benchmark for Interpretability Methods in Deep Neural Networks (Curran Associates, 2019)."},{"key":"692_CR74","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Proc. 31st International Conference on Neural Information Processing Systems (eds von Luxburg, U. et al.) 4768\u20134777 (Curran Associates Inc., 2017)."},{"key":"692_CR75","unstructured":"Alvarez-Melis, D. & Jaakkola, T. S. On the robustness of interpretability methods. ICML Workshop on Human Interpretability in Machine Learning (2018)."},{"key":"692_CR76","unstructured":"Agarwal, C. et al. Rethinking stability for attribution-based explanations. ICLR Pair2Struct Workshop (2022)."},{"key":"692_CR77","doi-asserted-by":"crossref","unstructured":"Mothilal, R. K., Sharma, A. & Tan, C. Explaining machine learning classifiers through diverse counterfactual explanations. In Proc. 2020 Conference on Fairness, Accountability, and Transparency 607\u2013617 (Association for Computing Machinery, 2020).","DOI":"10.1145\/3351095.3372850"},{"key":"692_CR78","doi-asserted-by":"crossref","unstructured":"Greenwell, B. M., Boehmke, B. C. & McCarthy, A. J. A simple and effective model-based variable importance measure. Preprint at https:\/\/arxiv.org\/abs\/1805.04755 (2018).","DOI":"10.32614\/CRAN.package.vip"},{"key":"692_CR79","doi-asserted-by":"publisher","unstructured":"Slack, D., Krishna, S., Lakkaraju, H. & Singh, S. TalkToModel: explaining machine learning models with interactive natural language conversations. Zenodo https:\/\/doi.org\/10.5281\/zenodo.7502206 (2022).","DOI":"10.5281\/zenodo.7502206"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00692-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00692-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00692-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T01:04:31Z","timestamp":1729818271000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00692-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,27]]},"references-count":79,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["692"],"URL":"https:\/\/doi.org\/10.1038\/s42256-023-00692-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2129845\/v1","asserted-by":"object"}]},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,27]]},"assertion":[{"value":"3 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}