Diffbrief Engineering daily

← Sunday, October 18, 2026Models & trainingPaper

LeanPRM uses Lean-checked proofs to train step-level verifiers

huggingface.co by Rodney Lafuente-Mercado et al. Editor score 8/10

LeanPRM creates 152K step labels across 10,634 proofs, and its Qwen3-4B verifier reaches 74.7% held-out step-label accuracy versus 48.2% for the base model. The results show how formal tools can supply training data for checking long natural-language proofs.

What
LeanPRM generates step-level labels for natural-language proofs by pairing them with formal proofs checked by Lean.
Method
A second model removes failures caused only by formal syntax, so negative labels identify mathematical errors; the resulting dataset has 152K labeled steps.
Why it matters
A Qwen3-4B verifier trained on LeanPRM reached 74.7 exact step-label accuracy on a held-out set, versus 60.3 for the same base model trained on PRM800K.
paired with checked by labels steps filters failu… natural-languageproof paired formalproof Lean second model LeanPRM
Lean checks paired proofs, then a second model filters syntax-only failures to create labeled data. Sketched from the article's own text.

Read on huggingface.co →

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.

Your note

Private to you. Stored in this browser, and synced to your account when you are signed in.