A reinforcement learning framework improves autoformalization without labeled data by rewarding outputs that pass Lean syntax and LLM consistency checks.
Interactive theorem proving and program development
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FormaRL: Enhancing Autoformalization with no Labeled Data
A reinforcement learning framework improves autoformalization without labeled data by rewarding outputs that pass Lean syntax and LLM consistency checks.