Rethinking Explanations: Formalizing Contrast in Description Logics

📰 ArXiv cs.AI

Learn to formalize contrast in description logics for better explanations in AI systems, and why it matters for user-centered approaches

advanced Published 5 May 2026

Action Steps

Read the abstract to understand the limitations of current explanation formalisms in description logics
Apply description logics to formalize contrast and improve explanations
Configure a knowledge base to incorporate user-centered approaches
Test the effectiveness of contrast formalization in description logics
Compare the results with existing explanation formalisms

Who Needs to Know This

AI researchers and knowledge engineers can benefit from this to improve explanation formalisms in description logic knowledge bases, enhancing user understanding and experience

Key Insight

💡 Formalizing contrast in description logics can lead to more user-centered explanations in AI systems

Key Takeaways

Learn to formalize contrast in description logics for better explanations in AI systems, and why it matters for user-centered approaches

Full Article

Title: Rethinking Explanations: Formalizing Contrast in Description Logics

Abstract:
arXiv:2605.01442v1 Announce Type: new Abstract: There has been a growing interest in explaining entailments over description logic (DL) knowledge bases. The existing explanation formalisms focus on justifications to explain true axioms, and abductive reasoning to explain missing axioms in a knowledge base. However, these formalisms only point out the reasoning steps behind a (missing) entailment and lack a user-centered approach as they do not consider an inquirer's needs, level of understanding

Read full paper → ← Back to Reads