AI Paper Atlas

Research map / Large language models / Agents, code and math

Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

Albert Qiaochu Jiang, Sean Welleck, Jin Peng Zhou, Timothee Lacroix, Jiacheng Liu, Wenda Li, Mateja Jamnik, Guillaume Lample, Yuhuai Wu

ICLR 2023 · Large language models › Agents, code and math · approach: Retrieval-augmented formal theorem proving · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Guide Sledgehammer with formal sketches derived from human informal proofsSledgehammer + heuristics · miniF2F-testsuccess rate: 20.9% -> 39.3%Improved
Guide the prover with sketches derived from Minerva 62B informal draftsSledgehammer + heuristics · miniF2F-validsuccess rate: 18.0% -> 43.9%Improved
Add 11 heuristic tacticsSledgehammer · miniF2F-testsuccess rate: 10.4% -> 20.9%Improved
Use Minerva 62B rather than Minerva 8B for informal proof draftingDSP · miniF2F-testsuccess rate: 35.3% -> 37.7%Improved
Use Minerva 540B rather than Minerva 62B for informal proof draftingDSP · miniF2F-testsuccess rate: 37.7% -> 38.9%; 43.9% -> 42.6%Mixed
Add in-line comments aligning informal proof segments with sketch code (ablation)DSP · miniF2F-validsuccess rate: 4.9%Improved
Add in-line comments aligning informal proof segments with sketch code (ablation)DSP · miniF2F-testsuccess rate: 2.8%Improved
Add informal proof drafts before sketching (ablation)DSP · miniF2F-validsuccess rate: 3.7%Improved
Add informal proof drafts before sketching (ablation)DSP · miniF2F-testsuccess rate: 5.3%Improved
Use automated provers to close open conjectures in sketches (ablation)DSP · miniF2F-validsuccess rate: 9.8%Improved
Use automated provers to close open conjectures in sketches (ablation)DSP · miniF2F-testsuccess rate: 9.0%Improved
Draft informal proofs with Minerva 540B rather than use human-written draftsDSP with 200 sketch attempts per problem · miniF2Fproblems solved: 203 -> 209Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy