#concept-bottleneck2 articles

2 articles

AIBullisharXiv – CS AI · 6h ago1

🧠

GlassMol: Interpretable Molecular Property Prediction with Concept Bottleneck Models

Researchers introduce GlassMol, a new interpretable AI model for molecular property prediction that addresses the black-box problem in drug discovery. The model uses Concept Bottleneck Models with automated concept curation and LLM-guided selection, achieving performance that matches or exceeds traditional black-box models across thirteen benchmarks.

AIBullisharXiv – CS AI · 6h ago1

🧠

Causal Neural Probabilistic Circuits

Researchers propose Causal Neural Probabilistic Circuits (CNPC), a new AI model that enhances interpretable machine learning by incorporating causal dependencies between concepts. The model allows domain experts to make corrections that properly propagate through causal relationships, achieving higher accuracy than baseline models across benchmark datasets.