Explainable and Transparent AI and Multi-Agent Systems - 5th International Workshop, EXTRAAMAS 2023, London, UK, May 29, 2023, Revised Selected Papers
Explainable and Transparent AI and Multi-Agent Systems - 5th International Workshop, EXTRAAMAS 2023, London, UK, May 29, 2023, Revised Selected Papers
复制标题
可解释和透明的人工智能和多代理系统 - 第五届国际研讨会，EXTRAAMAS 2023，英国伦敦，2023 年 5 月 29 日，修订后的精选论文
DOI：
10.1007/978-3-031-40878-6_4
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Xu Y
中科院分区：
文献类型：
--
作者：
Xu Y
人工智能系统解释自己的需求越来越被认为是一个优先事项，特别是在错误的决策可能导致伤害，甚至在最坏的情况下导致死亡的领域。可解释人工智能（XAI）试图为AI决策提供人类可理解的解释。然而，大多数XAI系统优先考虑技术复杂性和以研究为导向的目标等因素，而不是最终用户需求，从而存在信息过载的风险。本研究试图弥合目前的理解差距，并提供见解，帮助用户理解基于规则的系统的推理，通过对话。本研究的假设是，运用对话作为一种机制可以有效地构建解释。基于规则的人工智能系统的对话框架，允许系统解释其决策，从事“为什么？”为什么不呢问答我们建立了这个框架的正式属性，并提出了一个小的用户研究与令人鼓舞的结果，比较基于对话的解释与人工智能系统产生的证明树。
The need for AI systems to explain themselves is increasingly recognised as a priority, particularly in domains where incorrect decisions can result in harm and, in the worst cases, death. Explainable Artificial Intelligence (XAI) tries to produce human-understandable explanations for AI decisions. However, most XAI systems prioritize factors such as technical complexities and research-oriented goals over end-user needs, risking information overload. This research attempts to bridge a gap in current understanding and provide insights for assisting users in comprehending the rule-based system’s reasoning through dialogue. The hypothesis is that employingdialogueas a mechanism can be effective in constructing explanations. A dialogue framework for rule-based AI systems is presented, allowing the system to explain its decisions by engaging in “Why?” and “Why not?” questions and answers. We establish formal properties of this framework and present a small user study with encouraging results that compares dialogue-based explanations with proof trees produced by the AI System.