Explanation as Question Answering based on a Task Model of the Agent's Design
Explanation as Question Answering based on a Task Model of the Agent's Design
复制标题
DOI：
10.48550/arxiv.2206.05030
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Ashok K. Goel;Harsh Sikka;Vrinda Nandan;Jeonghyun Lee;Matt Lisle;S. Rugaber
中科院分区：
文献类型：
--
作者：
Ashok K. Goel;Harsh Sikka;Vrinda Nandan;Jeonghyun Lee;Matt Lisle;S. Rugaber
我们描述了一种对人工智能代理中解释生成的立场，这种立场既以人为中心，又基于设计。我们通过焦点小组的参与式设计收集关于人工智能代理工作的问题。我们通过一个任务-方法-知识模型来捕获代理的设计，该模型明确指定了代理的任务和目标，以及它用来完成任务的机制、知识和词汇。我们通过在Skill sync中生成解释来说明我们的方法，Skill sync是一种人工智能代理，将公司和大学联系起来，以提高工人的技能和重新技能。特别是，我们在Skill sync中嵌入了一个名为AskJill的问答代理，其中AskJill包含了Skill sync设计的TMK模型。AskJill目前回答了人类提出的关于Skill Sync任务和词汇的问题，从而帮助解释了它是如何产生推荐的。
We describe a stance towards the generation of explanations in AI agents that is both human-centered and design-based. We collect questions about the working of an AI agent through participatory design by focus groups. We capture an agent's design through a Task-Method-Knowledge model that explicitly specifies the agent's tasks and goals, as well as the mechanisms, knowledge and vocabulary it uses for accomplishing the tasks. We illustrate our approach through the generation of explanations in Skillsync, an AI agent that links companies and colleges for worker upskilling and reskilling. In particular, we embed a question-answering agent called AskJill in Skillsync, where AskJill contains a TMK model of Skillsync's design. AskJill presently answers human-generated questions about Skillsync's tasks and vocabulary, and thereby helps explain how it produces its recommendations.