Contestability in Quantitative Argumentation

2025-07-15

AI Summary

This paper addresses the core contestability problem in Edge-Weighted Quantitative Bipolar Argumentation Frameworks (EW-QBAFs): *how to adjust edge weights to achieve a desired strength for a target argument*. To this end, we propose Gradient-based Relation Attribution Explanations (G-RAEs), the first interpretability method tailored for weight tuning in EW-QBAFs. G-RAEs quantify the sensitivity of argument strength to individual edge weights and leverage these gradients in an iterative optimization algorithm that enables preference-guided, precise strength calibration. Evaluated on synthetic data mimicking recommendation systems and MLP architectures, G-RAEs demonstrate significant efficacy in steering argument strengths as intended. The approach markedly enhances human controllability and contestability of AI decisions, thereby establishing a novel paradigm for explainable and intervenable argumentative AI systems.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Contestable AI requires that AI-driven decisions align with human preferences. While various forms of argumentation have been shown to support contestability, Edge-Weighted Quantitative Bipolar Argumentation Frameworks (EW-QBAFs) have received little attention. In this work, we show how EW-QBAFs can be deployed for this purpose. Specifically, we introduce the contestability problem for EW-QBAFs, which asks how to modify edge weights (e.g., preferences) to achieve a desired strength for a specific argument of interest (i.e., a 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 G-RAEs, we develop an iterative algorithm that progressively adjusts the edge weights to attain the desired strength. We evaluate our approach experimentally on synthetic EW-QBAFs that simulate the structural characteristics of personalised recommender systems and multi-layer perceptrons, and demonstrate that it can solve the problem effectively.

Problem

• Enhancing AI contestability via EW-QBAFs for human-aligned decisions
• Modifying edge weights to achieve desired argument strength in EW-QBAFs
• Providing interpretable guidance for weight adjustments using G-RAEs

Innovation

• Uses gradient-based relation attribution explanations
• Modifies edge weights for desired argument strength
• Iterative algorithm adjusts weights progressively