Mariela Morveli-Espinoza
Papers
1
Total Citations
8
H-Index
1
About
Dr. Mariela Morveli-Espinoza is a leading voice in Explainable Artificial Intelligence (XAI) and multi-agent systems, with a particular focus on how intelligent agents can transparently communicate their reasoning to humans. Her most cited work, "Argumentation-Based Agents that Explain Their Decisions" (2019, 8 citations), introduces a novel extension of the Belief-Desire-Intention (BDI) model that enables agents to generate human-understandable explanations for their choices. This contribution addresses a critical challenge in AI: bridging the gap between complex internal decision-making processes and user trust. By leveraging argumentation theory, Dr. Morveli-Espinoza’s research provides a structured framework for agents to justify their actions, making AI systems more accountable and interpretable. Her work sits at the intersection of logic, reasoning, and human-computer interaction, offering practical tools for developing transparent autonomous systems. With a growing citation impact, she is recognized for advancing the theoretical foundations of XAI while tackling real-world needs for fairness and explainability in AI. Her research is essential reading for anyone interested in building ethical, trustworthy AI that can clearly articulate its decisions.
Research Focus
Key Achievements
Top Papers
- 1Argumentation-Based Agents that Explain Their Decisions8 citations · 2019