AI Paper Atlas

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

NaturalProver: Grounded Mathematical Proof Generation with Language Models

Sean Welleck, Jiacheng Liu, Ximing Lu, Hannaneh Hajishirzi, Yejin Choi

NeurIPS 2022 · Large language models › Agents, code and math · approach: Retrieval-augmented formal theorem proving · 7 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
Condition proof generation on human-provided reference titlesGPT-3 proof generation · NaturalProofs-Gen core test, full proofoverall usefulness: 20% -> 35%Improved
Condition proof generation on retrieved reference titlesGPT-3 proof generation · NaturalProofs-Gen core test, full proofoverall correctness: 13% -> 24%Improved
Use stepwise++ decoding with provided referencesNaturalProver · NaturalProofs-Gen core test, full proofoverall usefulness: 35% -> 45%Improved
Add reference reconstruction during training (ablation)NaturalProver with provided references · NaturalProofs-Gen core validation, full proofRef-F1: 82.85 -> 84.15Improved
Add reference reconstruction during training (ablation)NaturalProver with provided references · NaturalProofs-Gen core validation, full proofGLEU: 33.03 -> 35.93Improved
Add multi-temperature expansion (ablation)Stepwise++ decoding · NaturalProofs-Gen core dev, full proofRef-F1: 93.11 (.34) -> 94.13 (.45)Improved
Add selection across different constraint-weight settings (ablation)Stepwise++ decoding · NaturalProofs-Gen core dev, full proofRef-F1: 92.61 (.63) -> 94.13 (.45)Improved
Use stepwise++ rather than reranking 10 full proofs (ablation)NaturalProver decoding · NaturalProofs-Gen core dev, full proofRef-F1: 91.72 (.28) -> 94.13 (.45)Improved
Use reranking of 10 full proofs rather than stepwise++ (ablation)NaturalProver decoding · NaturalProofs-Gen core dev, full proofGLEU: 40.11 (1.55) -> 43.88 (.29)Improved
Increase constraint weight α from 0.0 to 1.0 (ablation)NaturalProver value function · NaturalProofs-Gen core dev, full proofRef-F1: 88.40 -> 93.60Improved
Increase constraint weight α from 0.0 to 1.0 (ablation)NaturalProver value function · NaturalProofs-Gen core dev, full proofGLEU: 42.79 -> 41.90Hurt
Increase GPT-2 inference-time compute by reranking 10 proofs (ablation)NaturalProver with GPT-2 · NaturalProofs-Gen core dev, full proofRef-F1: 65.22 -> 89.30Improved

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