When Does Structured Knowledge Help Neural Theorem Proving?
Does structured mathematical knowledge help LLMs prove theorems in Lean 4? If so, for which models, and does the answer vary by problem? Formal libraries such as Mathlib encode 285,000+ verified theorems with syntactic dependencies, but the semantic layer mathematicians rely on for discovery (analogies, generalizations...
Sareh Nabi, Roland Vogl, Marzieh Nabi
· 0 citations