Pith. sign in

REVIEW 14 cited by

Autoformalization with Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2205.12615 v1 pith:BDRKJI3S submitted 2022-05-25 cs.LG cs.AIcs.LOcs.SE

classification cs.LGcs.AIcs.LOcs.SE
keywords autoformalizationformallanguagegoalimprovinglargemodelsprocess
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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 $35.2\%$.

Discussion (0). Sign in to comment.

Forward citations

Cited by 14 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 of 10 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 of 10

    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 of 10

    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 of 10

    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 of 10

    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 of 10

    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 of 10

    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 of 10

    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. Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph

    cs.AI 2025-10 conditional novelty 6.0 of 10

    A graph-of-thought agent with retrieval and a term-grounded semantic checker auto-formalizes research-level math statements in Lean, hitting 68.5% on ProofNet and 6/14 homological conjectures where baselines score 0.

  10. FormaRL: Enhancing Autoformalization with no Labeled Data

    cs.AI 2025-08 conditional novelty 6.0 of 10

    A reinforcement learning framework improves autoformalization without labeled data by rewarding outputs that pass Lean syntax and LLM consistency checks.

  11. LeanFlow: A Case Study in Workflow-Driven Lean Autoformalization

    cs.AI 2026-06 conditional novelty 5.0 of 10

    Workflow control and a cached Lean verifier improve completion and token efficiency in document-to-project autoformalization.

  12. Automating Formal Verification with Reinforcement Learning and Recursive Inference

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    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.

  13. Explicit Formulas and Unimodality Phenomena for General Position Polynomials

    math.CO 2026-03 unverdicted novelty 5.0 of 10

    Explicit formulas for general position polynomials of complete multipartite graphs are given, with log-concavity and unimodality for balanced parts of size r≤4 and counterexamples for larger r and some coronas.

  14. Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning

    cs.AI 2025-09 conditional novelty 5.0 of 10

    Formal languages matter as the intermediate representation in neurosymbolic reasoning: first-order logic outperforms logic programming languages (ASP, Pyke) in average accuracy.

Pith tools