Citation

BibTex format

@inproceedings{Rago:2023:kr.2023/57,
author = {Rago, A and Li, H and Toni, F},
doi = {kr.2023/57},
pages = {582--592},
publisher = {IJCAI Organization},
title = {Interactive explanations by conflict resolution via argumentative exchanges},
url = {http://dx.doi.org/10.24963/kr.2023/57},
year = {2023}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - As the field of explainable AI (XAI) is maturing, calls forinteractive explanations for (the outputs of) AI models aregrowing, but the state-of-the-art predominantly focuses onstatic 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 ofcognitive biases in humans. We show experimentally (in asimulated 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.
AU - Rago,A
AU - Li,H
AU - Toni,F
DO - kr.2023/57
EP - 592
PB - IJCAI Organization
PY - 2023///
SN - 2334-1033
SP - 582
TI - Interactive explanations by conflict resolution via argumentative exchanges
UR - http://dx.doi.org/10.24963/kr.2023/57
UR - http://hdl.handle.net/10044/1/104734
ER -

Contact us

Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ

To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:

ai-speaker@imperial.ac.uk

To reach the network manager, Diana O'Malley - including to join the network - please contact:

ai-net-manager@imperial.ac.uk