Exploration of Neural Machine Translation in Autoformalization of Mathematics in Mizar
Not on the map. Why?
Abstract (arXiv)
In this paper we share several experiments trying to automatically translate informal mathematics into formal mathematics. In our context informal mathematics refers to human-written mathematical sentences in the LaTeX format; and formal mathematics refers to statements in the Mizar language. We conducted our experiments against three established neural network-based machine translation models that are known to deliver competitive results on translating between natural languages. To train these models we also prepared four informal-to-formal datasets. We compare and analyze our results according to whether the model is supervised or unsupervised. In order to augment the data available for auto-formalization and improve the results, we develop a custom type-elaboration mechanism and integrate it in the supervised translation.
Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 7; 2023: 6; 2024: 10; 2025: 9; 2026: 2.
40 papers.
Sort:
By area:
- 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 278
- 2022Autoformalization with Large Language Modelscited by 252
- 2022Memorizing Transformerscited by 219
- 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 161
- 2021Proof Artifact Co-training for Theorem Proving with Language Modelscited by 130
- 2021NaturalProofs: Mathematical Theorem Proving in Natural Languagecited by 80
- 2024Formal Mathematical Reasoning: A New Frontier in AIcited by 80
- 2022NaturalProver: Grounded Mathematical Proof Generation with Language Modelscited by 72
- 2024Lean-STaR: Learning to Interleave Thinking and Provingcited by 64
- 2024A Survey on Deep Learning for Theorem Provingcited by 55
- 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalizationcited by 53
- 2021LIME: Learning Inductive Bias for Primitives of Mathematical Reasoningcited by 46
28 more
- 2024Process-Driven Autoformalization in Lean 4cited by 45
- 2023Multilingual Mathematical Autoformalizationcited by 38
- 2023Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofscited by 27
- 2024Reliable Evaluation and Benchmarks for Statement Autoformalizationcited by 25
- 2023Lyra: Orchestrating Dual Correction in Automated Theorem Provingcited by 24
- 2025ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Datacited by 23
- 2022Towards a Mathematics Formalisation Assistant using Large Language Modelscited by 22
- 2022A Survey in Mathematical Language Processingcited by 9
- 2024REFACTOR: Learning to Extract Theorems from Proofscited by 9
- 2024GFLean: An Autoformalisation Framework for Lean via GFcited by 9
- 2025Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Taskscited by 9
- 2024Can Transformers Do Enumerative Geometry?cited by 8
- 2025Towards a Common Framework for Autoformalizationcited by 7
- 2025StepProof: Step-by-step verification of natural language mathematical proofscited by 6
- 2025RLMEval: Evaluating Research-Level Neural Theorem Provingcited by 6
- 2025Automated Formalization via Conceptual Retrieval-Augmented LLMscited by 5
- 2021A Study of Continuous Vector Representationsfor Theorem Provingcited by 4
- 2022A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspectivecited by 3
- 2021Smart Proofs via Smart Contracts: Succinct and Informative Mathematical Derivations via Decentralized Marketscited by 2
- 2025Improving Autoformalization Using Direct Dependency Retrievalcited by 2
- 2026MathAtlas: A Benchmark for Autoformalization in the Wildcited by 2
- 2021Disambiguating Symbolic Expressions in Informal Documentscited by 1
- 2023Improving the Diproche CNL through Autoformalization via Large Language Modelscited by 1
- 2025E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressionscited by 1
- 2025Hierarchical Attention Generates Better Proofscited by 1
- 2026Pipeline for Verifying LLM-Generated Mathematical Solutionscited by 1
- 2023Using Large Language Models for (De-)Formalization and Natural Argumentation Exercises for Beginner's Studentscited by 0
- 2024ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignmentcited by 0
- 2026MathAtlas: A Benchmark for Autoformalization in the Wild13 May 2026
- 2026Pipeline for Verifying LLM-Generated Mathematical Solutions24 Feb 2026
- 2025Improving Autoformalization Using Direct Dependency Retrieval15 Nov 2025
- 2025RLMEval: Evaluating Research-Level Neural Theorem Proving29 Oct 2025
- 2025Towards a Common Framework for Autoformalization11 Sep 2025
- 2025Automated Formalization via Conceptual Retrieval-Augmented LLMs9 Aug 2025
- 2025StepProof: Step-by-step verification of natural language mathematical proofs12 Jun 2025
- 2025Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks26 May 2025
- 2025Hierarchical Attention Generates Better Proofs27 Apr 2025
- 2025ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data8 Feb 2025
- 2025E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions24 Jan 2025
- 2024Formal Mathematical Reasoning: A New Frontier in AI20 Dec 2024
28 more
- 2024ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment23 Oct 2024
- 2024Can Transformers Do Enumerative Geometry?27 Aug 2024
- 2024Lean-STaR: Learning to Interleave Thinking and Proving14 Jul 2024
- 2024Reliable Evaluation and Benchmarks for Statement Autoformalization11 Jun 2024
- 2024Process-Driven Autoformalization in Lean 44 Jun 2024
- 2024A Survey on Deep Learning for Theorem Proving15 Apr 2024
- 2024GFLean: An Autoformalisation Framework for Lean via GF1 Apr 2024
- 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization26 Mar 2024
- 2024REFACTOR: Learning to Extract Theorems from Proofs26 Feb 2024
- 2023Multilingual Mathematical Autoformalization7 Nov 2023
- 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers23 Oct 2023
- 2023Lyra: Orchestrating Dual Correction in Automated Theorem Proving27 Sep 2023
- 2023Using Large Language Models for (De-)Formalization and Natural Argumentation Exercises for Beginner's Students12 Apr 2023
- 2023Improving the Diproche CNL through Autoformalization via Large Language Models12 Mar 2023
- 2023Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs5 Jan 2023
- 2022Towards a Mathematics Formalisation Assistant using Large Language Models14 Nov 2022
- 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs21 Oct 2022
- 2022A Survey in Mathematical Language Processing30 May 2022
- 2022NaturalProver: Grounded Mathematical Proof Generation with Language Models25 May 2022
- 2022Autoformalization with Large Language Models25 May 2022
- 2022Memorizing Transformers16 Mar 2022
- 2022A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective10 Feb 2022
- 2021NaturalProofs: Mathematical Theorem Proving in Natural Language24 Mar 2021
- 2021Proof Artifact Co-training for Theorem Proving with Language Models11 Feb 2021
- 2021Smart Proofs via Smart Contracts: Succinct and Informative Mathematical Derivations via Decentralized Markets5 Feb 2021
- 2021Disambiguating Symbolic Expressions in Informal Documents25 Jan 2021
- 2021A Study of Continuous Vector Representationsfor Theorem Proving22 Jan 2021
- 2021LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning15 Jan 2021
- 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 161
- 2024Formal Mathematical Reasoning: A New Frontier in AIcited by 80
- 2024Lean-STaR: Learning to Interleave Thinking and Provingcited by 64
- 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalizationcited by 53
- 2024Process-Driven Autoformalization in Lean 4cited by 45
- 2025Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Taskscited by 9
- 2026Pipeline for Verifying LLM-Generated Mathematical Solutionscited by 1
- 2026Pipeline for Verifying LLM-Generated Mathematical Solutions24 Feb 2026
- 2025Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks26 May 2025
- 2024Formal Mathematical Reasoning: A New Frontier in AI20 Dec 2024
- 2024Lean-STaR: Learning to Interleave Thinking and Proving14 Jul 2024
- 2024Process-Driven Autoformalization in Lean 44 Jun 2024
- 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization26 Mar 2024
- 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers23 Oct 2023
- 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 278
- 2022Autoformalization with Large Language Modelscited by 252
- 2022Memorizing Transformerscited by 219
- 2021NaturalProofs: Mathematical Theorem Proving in Natural Languagecited by 80
- 2022NaturalProver: Grounded Mathematical Proof Generation with Language Modelscited by 72
- 2024A Survey on Deep Learning for Theorem Provingcited by 55
- 2021LIME: Learning Inductive Bias for Primitives of Mathematical Reasoningcited by 46
- 2023Multilingual Mathematical Autoformalizationcited by 38
- 2023Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofscited by 27
- 2024Reliable Evaluation and Benchmarks for Statement Autoformalizationcited by 25
- 2023Lyra: Orchestrating Dual Correction in Automated Theorem Provingcited by 24
- 2025ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Datacited by 23
12 most cited of 30 All 30 (JSON)
- 2026MathAtlas: A Benchmark for Autoformalization in the Wild13 May 2026
- 2025RLMEval: Evaluating Research-Level Neural Theorem Proving29 Oct 2025
- 2025Towards a Common Framework for Autoformalization11 Sep 2025
- 2025StepProof: Step-by-step verification of natural language mathematical proofs12 Jun 2025
- 2025Hierarchical Attention Generates Better Proofs27 Apr 2025
- 2025ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data8 Feb 2025
- 2025E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions24 Jan 2025
- 2024ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment23 Oct 2024
- 2024Can Transformers Do Enumerative Geometry?27 Aug 2024
- 2024Reliable Evaluation and Benchmarks for Statement Autoformalization11 Jun 2024
- 2024A Survey on Deep Learning for Theorem Proving15 Apr 2024
- 2024GFLean: An Autoformalisation Framework for Lean via GF1 Apr 2024
12 newest of 30 All 30 (JSON)