Probabilistic reasoning with abstract argumentation frameworks
Abstract argumentation offers an appealing way of representing and evaluating arguments
and counterarguments. This approach can be enhanced by considering probability …
and counterarguments. This approach can be enhanced by considering probability …
[PDF][PDF] Relation-Based Counterfactual Explanations for Bayesian Network Classifiers.
We propose a general method for generating counterfactual explanations (CFXs) for a range
of Bayesian Network Classifiers (BCs), eg singleor multi-label, binary or multidimensional …
of Bayesian Network Classifiers (BCs), eg singleor multi-label, binary or multidimensional …
[HTML][HTML] A two-phase method for extracting explanatory arguments from Bayesian networks
Errors in reasoning about probabilistic evidence can have severe consequences. In the
legal domain a number of recent miscarriages of justice emphasises how severe these …
legal domain a number of recent miscarriages of justice emphasises how severe these …
Probabilistic argumentation: A survey
A Hunter, S Polberg, N Potyka, T Rienstra, M Thimm - 2021 - orca.cardiff.ac.uk
Argumentation is inherently pervaded by uncertainty, which can arise as a result of the
context in which argumentation is used, the kinds of agents that are involved in a given …
context in which argumentation is used, the kinds of agents that are involved in a given …
[PDF][PDF] Recourse under model multiplicity via argumentative ensembling
Model Multiplicity (MM), also known as predictive multiplicity or the Rashomon Effect, refers
to a scenario where multiple, equally performing machine learning (ML) models may be …
to a scenario where multiple, equally performing machine learning (ML) models may be …
A bayesian agent-based framework for argument exchange across networks
In this paper, we introduce a new framework for modelling the exchange of multiple
arguments across agents in a social network. To date, most modelling work concerned with …
arguments across agents in a social network. To date, most modelling work concerned with …
Proof with and without probabilities: Correct evidential reasoning with presumptive arguments, coherent hypotheses and degrees of uncertainty
Evidential reasoning is hard, and errors can lead to miscarriages of justice with serious
consequences. Analytic methods for the correct handling of evidence come in different …
consequences. Analytic methods for the correct handling of evidence come in different …
Persuasive contrastive explanations for Bayesian networks
Abstract Explanation in Artificial Intelligence is often focused on providing reasons for why a
model under consideration and its outcome are correct. Recently, research in explainable …
model under consideration and its outcome are correct. Recently, research in explainable …
[PDF][PDF] Explaining classifiers' outputs with causal models and argumentation
We introduce a conceptualisation for generating argumentation frameworks (AFs) from
causal models for the purpose of forging explanations for models' outputs. The …
causal models for the purpose of forging explanations for models' outputs. The …
[HTML][HTML] Efficient search for relevance explanations using MAP-independence in Bayesian networks
Image 1-independence is a novel concept concerned with explaining the (ir) relevance of
intermediate nodes for maximum a posteriori (Image 2) computations in Bayesian networks …
intermediate nodes for maximum a posteriori (Image 2) computations in Bayesian networks …