KG-Prover shows that traversing a ProofWiki-derived knowledge graph at inference time improves LLM theorem-proving accuracy on miniF2F, ProofNet, and MUSTARDSAUCE without extra fine-tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scaling Natural-Language Graph-Based Test Time Compute for Automated Theorem Proving
KG-Prover shows that traversing a ProofWiki-derived knowledge graph at inference time improves LLM theorem-proving accuracy on miniF2F, ProofNet, and MUSTARDSAUCE without extra fine-tuning.