A reinforcement learning framework improves autoformalization without labeled data by rewarding outputs that pass Lean syntax and LLM consistency checks.
Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The ever-growing complexity of mathematical proofs makes their manual verification by mathematicians very cognitively demanding. Autoformalization seeks to address this by translating proofs written in natural language into a formal representation that is computer-verifiable via interactive theorem provers. In this paper, we introduce a semantic parsing approach, based on the Universal Transformer architecture, that translates elementary mathematical proofs into an equivalent formalization in the language of the Coq interactive theorem prover. The same architecture is also trained to translate simple imperative code decorated with Hoare triples into formally verifiable proofs of correctness in Coq. Experiments on a limited domain of artificial and human-written proofs show that the models generalize well to intermediate lengths not seen during training and variations in natural language.
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.