y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#explainable-ai News & Analysis

181 articles tagged with #explainable-ai. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

181 articles
AINeutralarXiv – CS AI · Mar 34/104
🧠

Why Not? Solver-Grounded Certificates for Explainable Mission Planning

Researchers developed a new method for explaining satellite mission planning decisions using solver-grounded certificates that directly derive explanations from optimization models. The approach achieves perfect accuracy in explaining why scheduling requests are accepted or rejected, outperforming traditional post-hoc explanation methods that produce non-causal attributions 29% of the time.

AIBullisharXiv – CS AI · Mar 34/105
🧠

Extended Empirical Validation of the Explainability Solution Space

Researchers published an extended validation study of the Explainability Solution Space (ESS) framework, demonstrating its effectiveness across different domains including urban resource allocation systems. The study confirms ESS can systematically adapt to various governance roles and stakeholder configurations, positioning it as a generalizable tool for explainable AI strategy design.

AINeutralarXiv – CS AI · Mar 34/105
🧠

Strength Change Explanations in Quantitative Argumentation

Researchers introduce strength change explanations for quantitative argumentation graphs to make AI inference systems more contestable and explainable. The method describes how to modify argument strengths to achieve desired outcomes and demonstrates applications through heuristic search on layered graphs.

AIBullisharXiv – CS AI · Mar 24/107
🧠

Joint Distribution-Informed Shapley Values for Sparse Counterfactual Explanations

Researchers introduce COLA, a framework that refines counterfactual explanations in AI models by using optimal transport theory and Shapley values to achieve the same prediction changes with 26-45% fewer feature modifications. The method works across different datasets and models to create more actionable and clearer AI explanations.

$NEAR
AINeutralarXiv – CS AI · Mar 24/106
🧠

Rough Sets for Explainability of Spectral Graph Clustering

Researchers propose an enhanced methodology using rough set theory to improve explainability of Graph Spectral Clustering (GSC) algorithms. The approach addresses challenges in explaining clustering results, particularly when applied to text documents where spectral space embeddings lack clear relation to content.

← PrevPage 8 of 8