Year: 2025
Type: preprint
Abstract: Large language models have demonstrated remarkable capabilities in natural language processing tasks requiring multi-step logical reasoning capabilities, such as automated theorem proving. However, challenges persist within theorem proving, such as the identification of key mathematical concepts, understanding their interrelationships, and formalizing proofs correctly within natural language. We present KG-prover, a novel framework that leverages knowledge graphs mined from reputable mathematical texts to augment general-purpose LLMs to construct and formalize mathematical proofs. We also study the effects of scaling graph-based, test-time compute using KG-Prover, demonstrating significant performance improvements over baselines across multiple datasets. General-purpose LLMs improve up to 21\% on miniF2F-test when combined with KG-Prover, with consistent improvements ranging from 2-11\% on the ProofNet, miniF2F-test, and MUSTARD datasets. Furthermore, KG-Prover with o4-mini achieves 50\% on pass miniF2F-test. This work provides a promising approach for augmenting natural language proof reasoning with knowledge graphs without the need for additional finetuning.
Source: arXiv (Cornell University)
Authors: Li, Vincent, Knappe, Tim, Fu, Yule, Han, Kevin, Zhu, Kevin
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6891916613
Cites:
Cited by:
Related to: