{"type":"ScholarlyArticle","title":"Conversational Explanations of Machine Learning Predictions Through Class-contrastive Counterfactual Statements","authors":[{"name":"Kacper Sokol","slug":"kacper-sokol","given":"Kacper","family":"Sokol","affiliation":"Department of Computer Science , University of Bristol"},{"name":"Peter Flach","slug":"peter-flach","given":"Peter","family":"Flach","affiliation":"Department of Computer Science , University of Bristol"}],"abstract":"Machine learning models have become pervasive in our everyday life; they decide on important matters influencing our education, employment and judicial system. Many of these predictive systems are commercial products protected by trade secrets, hence their decision-making is opaque. Therefore, in our research we address interpretability and explainability of predictions made by machine learning models. Our work draws heavily on human explanation research in social sciences: contrastive and exemplar explanations provided through a dialogue. This user-centric design, focusing on a lay audience rather than domain experts, applied to machine learning allows explainees to drive the explanation to suit their needs instead of being served a precooked template.","doi":"10.24963/ijcai.2018/836","url":"https://ijcai.org/proceedings/2018/836","pdf":"https://ijcai.org/proceedings/2018/0836.pdf","markdown":"https://ijcai.org/proceedings/2018/836.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/836","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":836,"pages":{"first":5785,"last":5786},"keywords":["Multidisciplinary Topics and Applications: Human-Computer Interaction","Machine Learning: Classification","Machine Learning: Machine Learning","Natural Language Processing: Dialogue"],"videos":[],"references":[{"position":1,"raw":"[Kim et al., 2017] Been Kim, Justin Gilmer, Fernanda Vie- gas, Ulfar Erlingsson, and Martin Wattenberg. Tcav: Rel- ative concept importance testing with linear concept acti- vation vectors. arXiv preprint arXiv:1711.11279, 2017.","title":"Tcav: Relative concept importance testing with linear concept activation vectors","authors":"Kim","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Kusner et al., 2017] Matt J Kusner, Joshua Loftus, Chris Russell, and Ricardo Silva. Counterfactual fairness. In Ad- vances in Neural Information Processing Systems, pages 4069-4079, 2017.","title":"Counterfactual fairness","authors":"Matt J Kusner, Joshua Loftus, Chris Russell, Ricardo Silva","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Lipton, 2017] Zachary C Lipton. The doctor just won't ac- cept that! In Interpretable ML Symposium, 31st Con- ference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 2017.","title":"The doctor just won't accept that!","authors":"Zachary C Lipton","year":"2017","venue":"Interpretable ML Symposium, 31st Conference on Neural Information Processing Systems (NIPS 2017)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Miller et al., 2017] Tim Miller, Piers Howe, and Liz Sonen- berg. Explainable ai: Beware of inmates running the asy- lum. In IJCAI-17 Workshop on Explainable AI (XAI), page 36, 2017.","title":"Explainable ai: Beware of inmates running the asylum","authors":"Tim Miller, Piers Howe, Liz Sonenberg","year":"2017","venue":"IJCAI-17 Workshop on Explainable AI (XAI)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Miller, 2017] Tim Miller. Explanation in artificial intelli- gence: Insights from the social sciences. arXiv preprint arXiv:1706.07269, 2017.","title":"Explanation in artificial intelligence: Insights from the social sciences","authors":"Tim Miller, Miller","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ribeiro et al., 2016] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. Model-agnostic interpretability of machine learning. arXiv preprint arXiv:1606.05386, 2016.","title":"Model-agnostic interpretability of machine learning","authors":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Wachter et al., 2017] Sandra Wachter, Brent Mittelstadt, and Chris Russell. Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR. Harvard Journal of Law & Technology, (Forth- coming), 2017.","title":"Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR","authors":"Sandra Wachter, Brent Mittelstadt, Chris Russell","year":"2017","venue":"Harvard Journal of Law & Technology","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}