New paper proposes argumentation framework for Evaluative AI

A new position paper proposes computational argumentation as a foundational framework for Evaluative AI (EAI). EAI aims to assist human decision-making by presenting multiple competing hypotheses alongside supporting and refuting evidence, rather than a single recommendation. The authors advocate for argumentation to create explainable and contestable EAI systems, paving the way for future research into distributed and human-centered EAI. AI

IMPACT Proposes a new theoretical framework for AI systems that present competing hypotheses and evidence, potentially improving explainability and contestability in decision support.

RANK_REASON Academic paper proposing a new framework for AI systems. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• Bibliographic Explorer
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Evaluative AI
• Gotit.pub
• Hugging Face
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →