A new dataset structuring proofs by core techniques plus progressive multi-stage fine-tuning lets LLMs outperform baselines on informal theorem-proving benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning to Reason with Insight for Informal Theorem Proving
A new dataset structuring proofs by core techniques plus progressive multi-stage fine-tuning lets LLMs outperform baselines on informal theorem-proving benchmarks.