
Incorporating trial-and-error information during training and inference can significantly improve the performance of large language models in solving intuitionistic propositional logic theorems compared to models trained only on successful proof paths.


coremsg

leveraging-trial-and-error-data-to-enhance-large-language-model-performance-in-intuitionistic-propositional-logic-theorem-proving


Leveraging Trial-and-Error Data to Enhance Large Language Model Performance in Intuitionistic Propositional Logic Theorem Proving


title_rewrite


GFLean is an autoformalisation framework that translates simple mathematical statements expressed in a controlled natural language called Simplified ForTheL to corresponding expressions in the Lean theorem prover.


autoformalisation-framework-gflean-for-translating-simplified-natural-language-statements-to-lean-expressions


Autoformalisation Framework GFLean for Translating Simplified Natural Language Statements to Lean Expressions
