ProofWala: A Framework for Multilingual Proof Data Synthesis and Theorem-Proving
Researchers have developed ProofWala, a new framework designed to facilitate multilingual proof data synthesis and theorem-proving for neural approaches. This framework includes a reusable library for interacting with interactive theorem provers (ITPs) and supports project-wide analysis and parallel experimentation. By training models multilingually across different ITPs like Lean 4 and Rocq, the system demonstrates improved cross-lingual and cross-domain transfer capabilities, showing statistically significant gains in specific mathematical domains. AI
IMPACT Enables more robust and scalable research in formal verification and automated theorem-proving by facilitating multilingual data synthesis and cross-lingual transfer.