In this section
@inproceedings{Yin:2026,
author = {Yin, X and Potyka, N and Rago, A and Kampik, T and Toni, F},
publisher = {Knowledge Representation and Reasoning (KR)},
title = {Contestability in edge-weighted quantitative bipolar argumentation frameworks},
year = {2026}
}
TY - CPAPER
AB - Contestable AI requires that AI-driven decisions align withgiven preferences. Various types of argumentation frame-works have been shown to support forms of contestability. In this paper we focus on the little-studied Edge-Weighted Quantitative Bipolar Argumentation Frameworks (EW-QBAFs), where arguments have a base score as inQBAFs but attacks and supports (edges) are weighted. After generalising gradual semantics and properties thereof from QBAFs to EW-QBAFs, we introduce the contestability problem for EW-QBAFs, which asks how to modify edge weights to achieve a desired strength for a specific topic argument. To address this problem, we propose gradient-based relation attribution explanations (G-RAEs), which quantify the sensitivity of the topic argument’s strength to changes in individual edge weights, thus providing interpretable guidance for weight adjustments towards contestability. Building on GRAEs, we develop a heuristic algorithm that progressively adjusts the edge weights to attain the desired strength. We evaluate our approach experimentally on synthetic EW-QBAFsthat simulate the structural characteristics of personalised recommender systems and multi-layer perceptrons, demonstrating that it can support contestability effectively.
AU - Yin,X
AU - Potyka,N
AU - Rago,A
AU - Kampik,T
AU - Toni,F
PB - Knowledge Representation and Reasoning (KR)
PY - 2026///
TI - Contestability in edge-weighted quantitative bipolar argumentation frameworks
ER -