Arg2P: an argumentation framework for explainable intelligent systems

Calegari, Roberta; Omicini, Andrea; Pisano, Giuseppe; Sartor, Giovanni

doi:10.1093/logcom/exab089

Cited by 8 publications

(6 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These frameworks have been implemented in several reasoners available online. In this paper we consider Arg2P (Calegari et al 2022), a recent implementation of ASPIC + .…”

Section: Implementing the Use Case In Arg2pmentioning

confidence: 99%

Compliance checking on first-order knowledge with conflicting and compensatory norms: a comparison among currently available technologies

et al. 2023

Self Cite

View full text Add to dashboard Cite

This paper analyses and compares some of the automated reasoners that have been used in recent research for compliance checking. Although the list of the considered reasoners is not exhaustive, we believe that our analysis is representative enough to take stock of the current state of the art in the topic. We are interested here in formalizations at the first-order level. Past literature on normative reasoning mostly focuses on the propositional level. However, the propositional level is of little usefulness for concrete LegalTech applications, in which compliance checking must be enforced on (large) sets of individuals. Furthermore, we are interested in technologies that are freely available and that can be further investigated and compared by the scientific community. In other words, this paper does not consider technologies only employed in industry and/or whose source code is non-accessible. This paper formalizes a selected use case in the considered reasoners and compares the implementations, also in terms of simulations with respect to shared synthetic datasets. The comparison will highlight that lot of further research still needs to be done to integrate the benefits featured by the different reasoners into a single standardized first-order framework, suitable for LegalTech applications. All source codes are freely available at https://github.com/liviorobaldo/compliancecheckers, together with instructions to locally reproduce the simulations.

show abstract

“…These frameworks have been implemented in several reasoners available online. In this paper we consider Arg2P (Calegari et al 2022), a recent implementation of ASPIC + .…”

Section: Implementing the Use Case In Arg2pmentioning

confidence: 99%

Compliance checking on first-order knowledge with conflicting and compensatory norms: a comparison among currently available technologies

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…recently, (Raymond, Gunes, and Prorok 2020) define an argumentation-based human-agent architecture integrating regulatory compliance, suitable for human-agent path deconfliction and based on abstract argumentation (Dung 1995); (Panisson, McBurney, and Bordini 2021) develop a multi-agent frameworks whereby agents can exchange information to jointly reason with argument schemes and critical questions; and (de Tarlé, Bonzon, and Maudet 2022) let agents debate using a shared abstract argumentation framework. These works mostly focus on narrow settings using structured and abstract argumentation under extensionbased semantics, and mostly ignore the XAI angle ((Raymond, Gunes, and Prorok 2020;Calegari et al 2022) are exceptions). Instead, with XAI as our core drive, we focus on (quantitative) bipolar argumentation under gradual semantics, motivated by their usefulness in several XAI approaches (e.g.…”

Section: Related Workmentioning

confidence: 99%

Interactive Explanations by Conflict Resolution via Argumentative Exchanges

Rago

Toni

2023

Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning

View full text Add to dashboard Cite

As the field of explainable AI (XAI) is maturing, calls for interactive explanations for (the outputs of) AI models are growing, but the state-of-the-art predominantly focuses on static explanations. In this paper, we focus instead on interactive explanations framed as conflict resolution between agents (i.e. AI models and/or humans) by leveraging on computational argumentation. Specifically, we define Argumentative eXchanges (AXs) for dynamically sharing, in multi-agent systems, information harboured in individual agents’ quantitative bipolar argumentation frameworks towards resolving conflicts amongst the agents. We then deploy AXs in the XAI setting in which a machine and a human interact about the machine’s predictions. We identify and assess several theoretical properties characterising AXs that are suitable for XAI. Finally, we instantiate AXs for XAI by defining various agent behaviours, e.g. capturing counterfactual patterns of reasoning in machines and highlighting the effects of cognitive biases in humans. We show experimentally (in a simulated environment) the comparative advantages of these behaviours in terms of conflict resolution, and show that the strongest argument may not always be the most effective.

show abstract

“…3 It is built upon 2P-Kt-a reboot of the tuProlog [11,13] project offering a general, extensible, and interoperable ecosystem for logic programming and symbolic AI. Whereas a complete overview of the features of this specific implementation is out of the scope of this paper, we refer the reader to [9,7,24] for more details. In this section we focus on how to effectively distribute its argumentation process (evaluation of arguments).…”

Section: Distributed Argumentation In Arg2pmentioning

confidence: 99%

“…Arg2P [9] is a logic-based technology, offering a thorough instantiation of the ASPIC + framework [21] for structured argumentation. The purpose of this paper is to effectively distribute the argumentation process (evaluation of arguments) so as to enable the exploitation of Arg2P in the context of cooperative argumentation, according to the aforementioned perspective.…”

Section: Introductionmentioning

confidence: 99%