Explanation through Argumentation

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 argumentation-based dialogue as a technique for implementing Explainable AI in a human-robot system.

[1]  Elizabeth Sklar,et al.  HRTeam: a framework to support research on human/multi-robot interaction , 2013, AAMAS.

[2]  Anh Nguyen,et al.  A BDI agent architecture for dialogue modelling and coordination in a smart personal assistant , 2005, IEEE/WIC/ACM International Conference on Intelligent Agent Technology.

[3]  Joris Hulstijn,et al.  Dialogue Models for Inquiry and Transaction , 2000 .

[4]  Mani B. Srivastava,et al.  Enabling Intelligence Analysis through Agent-Support: the CISpaces Toolkit , 2015, AAMAS.

[5]  Peter McBurney,et al.  A denotational semantics for deliberation dialogues , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[6]  Roderic A. Girle,et al.  Commands in Dialogue Logic , 1996, FAPR.

[7]  Lee Lacy,et al.  Defense Advanced Research Projects Agency (DARPA) Agent Markup Language Computer Aided Knowledge Acquisition , 2005 .

[8]  Wamberto Weber Vasconcelos,et al.  Scrutable plan enactment via argumentation and natural language generation , 2014, AAMAS.

[9]  Peter McBurney,et al.  Representing Epistemic Uncertainty by Means of Dialectical Argumentation , 2001, Annals of Mathematics and Artificial Intelligence.

[10]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[11]  Trevor J. M. Bench-Capon,et al.  Argumentation in artificial intelligence , 2007, Artif. Intell..

[12]  D. Walton,et al.  Commitment in Dialogue: Basic Concepts of Interpersonal Reasoning , 1995 .

[13]  Elizabeth Sklar,et al.  Learning Spatial Models for Navigation , 2015, COSIT.

[14]  Elizabeth Sklar,et al.  Argumentation-based dialogue games for shared control in human-robot systems , 2015, HRI 2015.

[15]  Simon Parsons,et al.  A Generalization of Dung's Abstract Framework for Argumentation: Arguing with Sets of Attacking Arguments , 2006, ArgMAS.

[16]  Iyad Rahwan,et al.  Agreeing on plans through iterated disputes , 2010, AAMAS.

[17]  International Foundation for Autonomous Agents and MultiAgent Systems ( IFAAMAS ) , 2007 .

[18]  Peter McBurney,et al.  Games That Agents Play: A Formal Framework for Dialogues between Autonomous Agents , 2002, J. Log. Lang. Inf..

[19]  E. Sklar,et al.  An Argumentation Engine : ArgTrust , 2012 .

[20]  Elizabeth Sklar,et al.  Designing the HRTeam framework: lessons learned from a rough-and-ready human/multi-robot team , 2011, AAMAS'11.

[21]  Peter McBurney,et al.  Chance Discovery Using Dialectical Argumentation , 2001, JSAI Workshops.

[22]  Elizabeth Sklar,et al.  Evaluation of a trust-modulated argumentation-based interactive decision-making tool , 2015, Autonomous Agents and Multi-Agent Systems.

[23]  Elizabeth Sklar,et al.  A study measuring the impact of shared decision making in a human-robot team , 2017, Int. J. Robotics Res..

[24]  Maria Fox,et al.  PDDL+ Planning with Temporal Pattern Databases , 2017, AAAI Workshops.

[25]  Elizabeth Sklar,et al.  Analysis of empirical results on argumentation-based dialogue to support shared decision making in a human-robot team , 2016, 2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).

[26]  Elizabeth Sklar,et al.  Towards the application of argumentation-based dialogues for education , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[27]  Michael van Lent,et al.  An Explainable Artificial Intelligence System for Small-unit Tactical Behavior , 2004, AAAI.

[28]  Mohammad Q. Azhar,et al.  Toward an argumentation-based dialogue framework for human-robot collaboration , 2012, ICMI '12.

[29]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

[30]  Henry Prakken,et al.  DOI: 10.1017/S000000000000000 Printed in the United Kingdom Formal systems for persuasion dialogue , 2022 .

[31]  Elizabeth Sklar,et al.  Using argumentation to reason about trust and belief , 2012, J. Log. Comput..

[32]  Peter McBurney,et al.  What kind of argument are we going to have today? , 2005, AAMAS '05.

[33]  Bart Verheij,et al.  Dialectical Argumentation with Argumentation Schemes: An Approach to Legal Logic , 2003, Artificial Intelligence and Law.

[34]  Sarit Kraus,et al.  Argumentation Theory in the Field: An Empirical Study of Fundamental Notions , 2014, ArgNLP.

[35]  Sarvapali D. Ramchurn,et al.  Argumentation-based negotiation , 2003, The Knowledge Engineering Review.

[36]  S. G. Axline,et al.  Computer-based consultations in clinical therapeutics: explanation and rule acquisition capabilities of the MYCIN system. , 1975, Computers and biomedical research, an international journal.

[37]  Trevor J. M. Bench-Capon,et al.  Argumentation for Decision Support , 2006, DEXA.