mlsanityData to 7 Oct 2026

Teaching Temporal Logics to Neural Networks

arXiv 2003.04218 ↗First posted 6 Mar 2020cs.LO cs.AI cs.LGcited by 51

Not on the map. Why?

Abstract (arXiv)

We study two fundamental questions in neuro-symbolic computing: can deep learning tackle challenging problems in logics end-to-end, and can neural networks learn the semantics of logics. In this work we focus on linear-time temporal logic (LTL), as it is widely used in verification. We train a Transformer on the problem to directly predict a solution, i.e. a trace, to a given LTL formula. The training data is generated with classical solvers, which, however, only provide one of many possible solutions to each formula. We demonstrate that it is sufficient to train on those particular solutions to formulas, and that Transformers can predict solutions even to formulas from benchmarks from the literature on which the classical solver timed out. Transformers also generalize to the semantics of the logics: while they often deviate from the solutions found by the classical solvers, they still predict correct solutions to most formulas.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 12; 2023: 11; 2024: 8; 2025: 12; 2026: 2.

51 papers.

Sort:

By area:

  1. 2022Autoformalization with Large Language Modelscited by 252
  2. 2022FOLIO: Natural Language Reasoning with First-Order Logiccited by 233
  3. 2022Memorizing Transformerscited by 219
  4. 2022End-to-end symbolic regression with transformerscited by 195
  5. 2021Proof Artifact Co-training for Theorem Proving with Language Modelscited by 130
  6. 2022On the Paradox of Learning to Reason from Datacited by 93
  7. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  8. 2023A Comprehensive Survey on Applications of Transformers for Deep Learning Taskscited by 70
  9. 2024LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Modelscited by 67
  10. 2023Length Generalization in Arithmetic Transformerscited by 64
  11. 2021Linear algebra with transformerscited by 62
  12. 2023ODEFormer: Symbolic Regression of Dynamical Systems with Transformerscited by 58
38 more
  1. 2023nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Modelscited by 57
  2. 2023Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Modelscited by 35
  3. 2022Formal Specifications from Natural Languagecited by 33
  4. 2023DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformerscited by 22
  5. 2021Neural Circuit Synthesis from Specification Patternscited by 17
  6. 2021Teaching Autoregressive Language Models Complex Tasks By Demonstrationcited by 15
  7. 2023Iterative Circuit Repair Against Formal Specificationscited by 9
  8. 2021Generating Symbolic Reasoning Problems with Transformer GANscited by 5
  9. 2022Learning to Find Proofs and Theorems by Learning to Refine Search Strategies: The Case of Loop Invariant Synthesiscited by 5
  10. 2024Guiding Multi-agent Multi-task Reinforcement Learning by a Hierarchical Framework with Logical Reward Shapingcited by 4
  11. 2025Al-Khwarizmi: Discovering Physical Laws with Foundation Modelscited by 4
  12. 2025Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalizationcited by 4
  13. 2024NeuroSynt: A Neuro-symbolic Portfolio Solver for Reactive Synthesiscited by 3
  14. 2024OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialogcited by 3
  15. 2025Logical forms complement probability in understanding language model (and human) performancecited by 3
  16. 2022Learning Temporal Rules from Noisy Timeseries Datacited by 2
  17. 2022OCTAL: Graph Representation Learning for LTL Model Checkingcited by 2
  18. 2023Using Language Models For Knowledge Acquisition in Natural Language Reasoning Problemscited by 2
  19. 2023Lightweight Online Learning for Sets of Related Problems in Automated Reasoningcited by 2
  20. 2023Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Modelscited by 2
  21. 2024Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalencecited by 2
  22. 2024Towards Specification-Driven LLM-Based Generation of Embedded Automotive Softwarecited by 2
  23. 2025Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanationscited by 2
  24. 2022Neural Combinatorial Logic Circuit Synthesis from Input-Output Examplescited by 1
  25. 2022Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?cited by 1
  26. 2024Learning Better Representations From Less Data For Propositional Satisfiabilitycited by 1
  27. 2024Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mambacited by 1
  28. 2025Propositional Logic for Probing Generalization in Neural Networkscited by 1
  29. 2025Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformerscited by 1
  30. 2025How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled Autonomycited by 1
  31. 2025RNN Generalization to Omega-Regular Languagescited by 1
  32. 2022Attention Flows for General Transformerscited by 0
  33. 2023OCTAL: Graph Representation Learning for LTL Model Checkingcited by 0
  34. 2025Studying number theory with deep learning: a case study with the M"obius and squarefree indicator functionscited by 0
  35. 2025LTLZinc: a Benchmarking Framework for Continual Learning and Neuro-Symbolic Temporal Reasoningcited by 0
  36. 2025Handling Open-Vocabulary Constructs in Formalizing Specifications: Retrieval-Augmented Parsing with Expert Knowledgecited by 0
  37. 2025Learning Representations Through Contrastive Neural Model Checkingcited by 0
  38. 2026Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learningcited by 0

50 most cited of 51 All 51 (JSON)