Pith

open record

sign in

arxiv: 2205.12615 · v1 · pith:BDRKJI3S · submitted 2022-05-25 · cs.LG · cs.AI· cs.LO· cs.SE

Autoformalization with Large Language Models

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:BDRKJI3Srecord.jsonopen to challenge →

classification cs.LG cs.AIcs.LOcs.SE
keywords autoformalizationformallanguagegoalimprovinglargemodelsprocess
0
0 comments X
read the original abstract

Autoformalization is the process of automatically translating from natural language mathematics to formal specifications and proofs. A successful autoformalization system could advance the fields of formal verification, program synthesis, and artificial intelligence. While the long-term goal of autoformalization seemed elusive for a long time, we show large language models provide new prospects towards this goal. We make the surprising observation that LLMs can correctly translate a significant portion ($25.3\%$) of mathematical competition problems perfectly to formal specifications in Isabelle/HOL. We demonstrate the usefulness of this process by improving a previously introduced neural theorem prover via training on these autoformalized theorems. Our methodology results in a new state-of-the-art result on the MiniF2F theorem proving benchmark, improving the proof rate from $29.6\%$ to $35.2\%$.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Machine-Verified Proof of a Quantum-Optimization Conjecture

    quant-ph 2026-06 accept novelty 8.0 full

    A Lean 4 machine-verified proof establishes that depth-p QAOA on the ring of disagrees attains approximation ratio (2p+1)/(2p+2) exactly.

  2. TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics

    cs.AI 2026-06 unverdicted novelty 8.0

    TheoremBench is a Lean4 benchmark of classical theorems in main and premised forms that evaluates LLM provers on partial progress, coverage, and token efficiency rather than binary success on competition problems.

  3. MathAtlas: A Benchmark for Autoformalization in the Wild

    cs.AI 2026-05 accept novelty 8.0

    MathAtlas is the first large-scale benchmark for autoformalizing graduate mathematics, where even strong models reach only 9.8% correctness on theorem statements and drop to 2.6% on the hardest dependency-deep subset.

  4. PAL: Program-aided Language Models

    cs.CL 2022-11 conditional novelty 8.0

    PAL improves few-shot reasoning accuracy by having LLMs generate executable programs rather than text-based chains of thought, outperforming much larger models on math and logic benchmarks.

  5. LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization

    cs.AI 2026-06 unverdicted novelty 7.0

    LeanMarathon uses four contract-scoped agents on an evolving blueprint coordinated by a two-stage orchestrator to formalize seven theorems from Erdős problems in Lean, proving 258 lemmas with no sorry across three runs.

  6. A Learning Method for Symbolic Systems Using Large Language Models

    cs.SE 2026-05 unverdicted novelty 7.0

    LLM2Ltac mines symbolic tactics from 11,725 Coq theorems using LLMs and integrates them into CoqHammer, improving proof rates by 23.87% on 6,199 theorems from four large verification projects.

  7. Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy

    cs.CL 2026-04 unverdicted novelty 7.0

    LLMs display clear performance stratification on formal language tasks aligned with Chomsky hierarchy complexity levels, limited by severe efficiency barriers rather than absolute capability.

  8. Lean Atlas: An Integrated Proof Environment for Scalable Human-AI Collaborative Formalization

    cs.HC 2026-03 conditional novelty 7.0

    Lean Atlas visualizes Lean 4 dependency graphs and applies Lean Compass to reduce the nodes needing human semantic review by 27-99% across six evaluated projects.

  9. Automating Formal Verification with Reinforcement Learning and Recursive Inference

    cs.LG 2026-05 unverdicted novelty 5.0

    RLVR training raises verified Dafny pass rates from 9.7% to 31.1% on a filtered benchmark while a Lean proof scaffold lifts success from 46.2% to 69.2% on a pilot set and solves 7 of 42 prior unsolved tasks.