Representation, justification, and explanation in a value-driven agent: an argumentation-based approach

Abstract

Ethical and explainable artificial intelligence is an interdisciplinary research area involving computer science, philosophy, logic, and social sciences, etc. For an ethical autonomous system, the ability to justify and explain its decision-making is a crucial aspect of transparency and trustworthiness. This paper takes a Value-Driven Agent (VDA) as an example, explicitly representing implicit knowledge of a machine learning-based autonomous agent and using this formalism to justify and explain the decisions of the agent. For this purpose, we introduce a novel formalism to describe the intrinsic knowledge and solutions of a VDA in each situation. Based on this formalism, we formulate an approach to justify and explain the decisionmaking process of a VDA, in terms of a typical argumentation formalism, Assumption-based Argumentation (ABA). As a result, a VDA in a given situation is mapped onto an argumentation framework in which arguments are defined by the notion of deduction. Justified actions with respect to semantics from argumentation correspond to solutions of the VDA. The acceptance (rejection) of arguments and their premises in the framework provides an explanation for why an action was selected (or not). Furthermore, we go beyond the existing version of VDA, considering not only practical reasoning, but also epistemic reasoning, such that the inconsistency of knowledge of the VDA can be identified, handled, and explained.

Argumentation and explainable artificial intelligence: a survey

“…Social relations and Argumentation are also the topic of Liao et al . (2018), for action selection of a robotic platform.…”

Beyond explainability: justifiability and contestability of algorithmic decision systems

“…The "human-in-the-loop" approach leverages on human feedback during the training process to obtain more accurate classifiers [46]. A lot of work has also been done on argumentation and dialog games [6,11,51,53] but the focus in these areas is generally the logical structure of the framework to express and to relate arguments or the protocol to exchange arguments. Closer to the notion of justification, [43] relies on "debates" between two competing algorithms exchanging arguments and counterarguments to convince a human user that their classification is correct.…”

Perspectives about artificial moral agents

“…The breadth of different AMA design approaches reported in the literature reveals a lack of consensus among scholars working on the Machine Ethics project and raises questions about whether it is possible to develop an objective validation of AMAs that avoids designer bias and ensures explainability [22,42,53,64].…”