Search papers, labs, and topics across Lattice.
2
0
3
LLMs can achieve high compilation rates in formal reasoning by either fabricating axioms during proof generation or subtly mistranslating premises, revealing a critical gap between proof validity and formalization faithfulness.
Forget toy problems: SorryDB offers a continuously updated stream of real-world Lean formalization tasks, providing a robust benchmark for AI provers to contribute to novel mathematics.
