Free argumentative exchanges for explaining image classifiers
File(s)
Published version
Author(s)
Kori, Avinash
Rago, antonio
Toni, Francesca
Type
Conference Paper
Abstract
Deep learning models are powerful image classifiers but their opacity hinders their trustworthiness. Explanation methods for capturing the reasoning process within these classifiers faithfully and in a cognitively manageable manner are scarce, due to their sheer complexity and size. In this paper, we provide a solution for this problem by defining a novel method for explaining the outputs of image classifiers with debates between two agents, each arguing for a particular class. We obtain these debates as concrete instances of Free Argumentative eXchanges (FAXs), a novel argumentation-based multi-agent framework allowing agents to internalise opinions by other agents differently than originally stated. We define two metrics to assess the usefulness of FAXs as argumentative explanations
for image classifiers. We then conduct a number of empirical experiments showing that FAXs perform well along these metrics as well as being more faithful to the image classifiers than conventional, non-argumentative explanation methods.
for image classifiers. We then conduct a number of empirical experiments showing that FAXs perform well along these metrics as well as being more faithful to the image classifiers than conventional, non-argumentative explanation methods.
Date Issued
2025-06-05
Date Acceptance
2024-12-19
Citation
AAMAS '25: Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, 2025, pp.1172-1180
ISBN
9798400714269
Publisher
ACM
Start Page
1172
End Page
1180
Journal / Book Title
AAMAS '25: Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems
Copyright Statement
© 2025 International Foundation for Autonomous Agents and Multiagent Systems. This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/).
License URL
Source
AAMAS 2025
Subjects
Argumentation
Explainable AI
Quantization
Publication Status
Published
Start Date
2025-05-19
Finish Date
2025-05-23
Coverage Spatial
Detroit, Michigan, USA