BibTex format

author = {Rago, A and Baroni, P and Toni, F},
publisher = {IJCAI Organisation},
title = {Explaining causal models with argumentation: the case of bi-variate reinforcement},
url = {},
year = {2022}

RIS format (EndNote, RefMan)

AB - Causal models are playing an increasingly important role inmachine learning, particularly in the realm of explainable AI.We introduce a conceptualisation for generating argumenta-tion frameworks (AFs) from causal models for the purposeof forging explanations for the models’ outputs. The concep-tualisation is based on reinterpreting desirable properties ofsemantics of AFs as explanation moulds, which are meansfor characterising the relations in the causal model argumen-tatively. We demonstrate our methodology by reinterpretingthe property of bi-variate reinforcement as an explanationmould to forge bipolar AFs as explanations for the outputs ofcausal models. We perform a theoretical evaluation of theseargumentative explanations, examining whether they satisfy arange of desirable explanatory and argumentative propertie
AU - Rago,A
AU - Baroni,P
AU - Toni,F
PB - IJCAI Organisation
PY - 2022///
SN - 2334-1033
TI - Explaining causal models with argumentation: the case of bi-variate reinforcement
UR -
ER -