Argumentation Proposed as Foundation for Explainable, Contestable Evaluative AI

Xiang Yin, Tim Miller, Nico Potyka, Antonio Rago, Francesca Toni· August 11, 2026 View original

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

HealthcareLegalFinanceGovernmentConsulting

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.

Evaluative AI (EAI) aims to assist human decision-making by offering multiple hypotheses along with supporting and refuting evidence, rather than just a single recommendation. This approach seeks to enhance transparency and allow for human scrutiny of AI outputs. Researchers are proposing computational argumentation as a robust framework to underpin EAI. This paradigm would provide a formal, computable basis for building EAI systems that are inherently explainable and open to contestation. This work lays the groundwork for a long-term research agenda focused on developing distributed and human-centered EAI systems, emphasizing the importance of clear reasoning and accountability in AI applications.

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

  1. 1Investigate argumentation frameworks for AI explainability in current projects.
  2. 2Pilot EAI concepts in low-risk decision support systems to gather feedback.
  3. 3Collaborate with AI researchers to integrate formal argumentation into AI development.
  4. 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 X

Originally 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 courses

More in AI Research

AI ResearchAI Engineering & DevTools

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.

Ryoya YamasakiAug 11, 2026
AI ResearchAI Engineering & DevTools

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.

Andrea Combette, Nelly Pustelnik, Antoine VenailleAug 11, 2026
AI Engineering & DevToolsAI Research

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.

Blessings MambweAug 11, 2026