3 papers
cs.PL2026
ProofGap: Benchmarking Step-Level Formal Reasoning with Local Obligations Derived from Natural-Language Solutions
Lihan Xie, Zhicheng Hui, Yingjun Lan +7
Existing formal mathematics benchmarks, such as miniF2F, ProofNet, and PutnamBench, primarily evaluate models on constructing complete formal proofs for challenging problems. Becau…
cs.LO2026
Verifiable Auto-Formalization of Mathematics Using a Relaxed Natural Formal Language
Zhicheng Hui, Lihan Xie, Xingzhi Qi +3
Auto-formalization aims to translate informal mathematical content into formal languages that can be processed by theorem provers. However, directly targeting existing theorem prov…
cs.PL2024
A Natural Formalized Proof Language
Lihan Xie, Zhicheng Hui, Qinxiang Cao
Artificial intelligence assisted mathematical proof has become a highly focused area nowadays. One key problem in this field is to generate formal mathematical proofs from natural…