Explanation through Argumentation

Abstract

Computational Argumentation is a logical model of reasoning that has its origins in philosophy and provides a means for organising evidence for (or against) particular claims (or decisions). Argumentation-based Dialogue is a related methodology that is used for structuring interactions between two (or more) agents and has been explored within the Multi-Agent Systems community as an extended form of negotiation where agents can not only exchange claims, but also their reasons for believing (or disbelieving) those claims. Recently, the Artificial Intelligence (AI) community has become intrigued by the notion of "Explainable AI", in which intelligent systems are able to explain predictions or decisions to (human) users. There is a natural pairing between Explainable AI and Argumentation: the first requires the need to clarify and defend decisions and the second provides a method for linking any decision to the evidence supporting it. In this paper, we describe how the two are connected and illustrate the utility of argumentationbased dialogue as a technique for implementing Explainable AI in a human-robot system. CCS CONCEPTS• Computing methodologies → Knowledge representation and reasoning; • Human-centered computing → User studies;

What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research

“…Developer [5,14,55,105] Safety Assess and increase a system's safety Deployer, User [44,58,69,70,74,78,105] Satisfaction Have satisfying systems User [5,13,15,24,28,33,36,39,43,46,78,79,94,102] [31]…”

Assumption-based argumentation with preferences and goals for patient-centric reasoning with interacting clinical guidelines

“…Argumentation is indeed well-suited for explainable reasoning [6,40,70] with argumentative explanations proposed in various settings, see e.g. [1][2][3]5,14,16,18,[21][22][23][24]26,28,31,32,[37][38][39]42,43,51,57,58,62,64,66,69,70,77,79,81,[84][85][86][87][88]90,93,101,103,104,[110][111][112]. We hope to exploit the well-established as well as novel ABA + mechanisms to our advantage of providing various explanations to accompany the decisions supported by ABA + G. In addition to several other future work directions mentioned in Sections 6 and 7, we will aim…”

Argumentation and explainable artificial intelligence: a survey

“…Argumentation for shared decision-making between a robotic platform and a human is the topic in Sklar and Azhar (2015, 2018), Azhar and Sklar (2016, 2017). To the best of our knowledge, these were the first studies on argumentation-based dialogue games between a human and a robotic platform.…”

“…The authors developed an LBAF along with a GUI that helps humans in cooperation with a robotic platform to reach a shared decision at each step of an activity, more specifically in a Treasure Hunt Game (Sklar & Azhar, 2015). Next, in Azhar and Sklar (2016, 2017), Sklar and Azhar (2018), the authors extent the Treasure Hunt Game with different methodologies for implementing multiple types of argumentation-based dialogues. The framework can explain which dialogues are appropriate given the beliefs of the participants and how multiple dialogues can occur simultaneously while containing consistency in the general dialogue.…”