Argumentation Proposed as Foundation for Explainable, Contestable Evaluative AI
Key takeaways
- Evaluative AI supports decisions by presenting competing hypotheses and evidence.
- Computational argumentation provides a formal foundation for explainable and contestable AI.
- This approach aims to build more trustworthy and human-centered AI systems.
- Explainability and contestability are crucial for AI adoption in critical domains.
Who benefits
Summary
This paper advocates for computational argumentation as a formal, computable foundation for Evaluative AI (EAI). The goal is to create EAI systems that support human decision-making by presenting competing hypotheses with evidence, making them explainable and contestable.
Why it matters
Professionals need AI systems that are not black boxes but can explain their reasoning and be challenged, especially in critical decision-making contexts. This research offers a path towards more trustworthy and accountable AI.
How to implement this in your domain
- 1Investigate argumentation frameworks for AI explainability in current projects.
- 2Pilot EAI concepts in low-risk decision support systems to gather feedback.
- 3Collaborate with AI researchers to integrate formal argumentation into AI development.
- 4Develop internal guidelines for explainable AI design based on argumentative principles.
Original post by Xiang Yin, Tim Miller, Nico Potyka, Antonio Rago, Francesca Toni
"arXiv:2608.07473v1 Announce Type: new Abstract: Evaluative AI (EAI) has been recently proposed as a way to support human decision-making, not by producing a single recommendation, but by presenting competing hypotheses together with evidence for and against each. In this position…"
View on XOriginally posted by Xiang Yin, Tim Miller, Nico Potyka, Antonio Rago, Francesca Toni on X · view source
Want to go deeper?
Turn these trends into skills with Learnijoy's hands-on AI & tech courses.
Explore coursesMore in AI Research
New Regularization Method Improves Ordinal Regression Performance
This study introduces a novel unimodality-promoting regularized learning (UPRL) method for ordinal regression that more strictly reflects the idea of promoting unimodal conditional probability distributions (CPDs). The new method avoids a scale-related bias found in previous UPRL approaches, leading to improved prediction performance, especially with smaller training datasets.
Criticality Governs Learning Dynamics in Deep Neural Networks
This research establishes a direct link between correlation propagation and the Neural Tangent Kernel (NTK) in deep neural networks, showing that optimal information and gradient flow occurs at a specific critical point. At this point, the NTK becomes proportional to output correlation, clarifying the role of orthogonal initialization in controlling learning dynamics.
PRISM Protocol Optimizes Permutation Search Strategies with Landscape Diagnostics
PRISM is a predictive protocol that diagnoses a fitness landscape before selecting a search strategy for permutation optimization problems. It uses inexpensive metrics to predict optimal mutation operators and determine when structured search is beneficial, demonstrating significant performance variations based solely on ordering in various AI and scientific machine learning tasks.