Machine Learning (ML) models are increasingly used to make critical decisions in real-world applications, yet they have become more complex, making them harder to understand. To this end, researchers have proposed several techniques to explain model predictions. However, practitioners struggle to use these explainability techniques because they often do not know which one to choose and how to interpret the results of the explanations. In this work, we address these challenges by introducing TalkToModel: an interactive dialogue system for explaining machine learning models through conversations. Specifically, TalkToModel comprises of three key components: 1) a natural language interface for engaging in conversations, making ML model explainability highly accessible, 2) a dialogue engine that adapts to any tabular model and dataset, interprets natural language, maps it to appropriate explanations, and generates text responses, and 3) an execution component that constructs the explanations. We carried out extensive quantitative and human subject evaluations of TalkToModel. Overall, we found the conversational system understands user inputs on novel datasets and models with high accuracy, demonstrating the system's capacity to generalize to new situations. In real-world evaluations with humans, 73% of healthcare workers (e.g., doctors and nurses) agreed they would use TalkToModel over baseline point-and-click systems for explainability in a disease prediction task, and 85% of ML professionals agreed TalkToModel was easier to use for computing explanations. Our findings demonstrate that TalkToModel is more effective for model explainability than existing systems, introducing a new category of explainability tools for practitioners. Code & demo released here: https://github.com/dylan-slack/TalkToModel.

翻译：机器学习（ML）模型越来越多地被用于现实应用中的关键决策，然而这些模型也变得更加复杂，使其难以理解。为此，研究人员提出了多种解释模型预测的技术。然而，实践者在运用这些可解释性技术时面临困难，因为他们往往不知道选择哪种方法，以及如何解读解释结果。在本研究中，我们通过引入TalkToModel来应对这些挑战：一个通过对话解释机器学习模型的交互式对话系统。具体而言，TalkToModel由三个关键组件构成：1）自然语言接口，用于进行对话，使ML模型的可解释性高度可访问；2）对话引擎，可适配任何表格模型和数据集，解析自然语言，将其映射到适当的解释，并生成文本响应；以及3）执行组件，用于构建解释。我们对TalkToModel进行了广泛的定量评估和人类受试者评估。总体而言，我们发现该对话系统能够以高精度理解用户对新型数据集和模型的输入，展示了系统泛化到新场景的能力。在真实世界的人类评估中，73%的医疗工作者（如医生和护士）表示在疾病预测任务中，相比于基于点击的基线系统，他们更愿意使用TalkToModel进行可解释性分析；85%的ML专业人士认为TalkToModel在计算解释方面更易于使用。我们的研究结果表明，TalkToModel在模型可解释性方面比现有系统更有效，为实践者引入了一类新的可解释性工具。代码与演示发布在：https://github.com/dylan-slack/TalkToModel。