Antonio Rago

Adapting the DF-QuAD algorithm to bipolar argumentation

2016 · Spiral (Imperial College London)

We define a quantitative semantics for evaluating the strength of arguments in Bipolar Argumentation frameworks (BAFs) by adapting the Discontinuity-Free QuAD (DF-QuAD) algorithm previously used for evaluating the strength of arguments in Quantitative Argumentation Debates …

Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation

2023 · arXiv (Cornell University)

Counterfactual Explanations (CEs) have received increasing interest as a major methodology for explaining neural network classifiers. Usually, CEs for an input-output pair are defined as data points with minimum distance to the input that are …

Advancing Interactive Explainable AI via Belief Change Theory

2024 · arXiv (Cornell University)

As AI models become ever more complex and intertwined in humans' daily lives, greater levels of interactivity of explainable AI (XAI) methods are needed. In this paper, we propose the use of belief change theory …

Aggregating bipolar opinions through bipolar assumption-based argumentation

2024 · Autonomous Agents and Multi-Agent Systems

Abstract We introduce a novel method to aggregate bipolar argumentation frameworks expressing opinions of different parties in debates. We use Bipolar Assumption-based Argumentation (ABA) as an all-encompassing formalism for bipolar argumentation under different semantics. By …

Evaluating Uncertainty Quantification Methods in Argumentative Large Language Models

2025 · ArXiv.org

Research in uncertainty quantification (UQ) for large language models (LLMs) is increasingly important towards guaranteeing the reliability of this groundbreaking technology. We explore the integration of LLM UQ methods in argumentative LLMs (ArgLLMs), an explainable …