#artificial intelligence
May 2025
From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark
An ARC solver is introduced, Knowledge Augmentation for Abstract Reasoning (KAAR), which encodes core knowledge priors within an ontology that classifies priors into three hierarchical levels based on their dependencies and maintains strong generalization across most LLMs.
Chao Lei, N. Lipovetzky, Krista A. Ehinger et al.
· arXiv.org · 2 citations