mlsanityData to 14 Oct 2026

Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

arXiv 1711.09576 ↗First posted 27 Nov 2017cs.LG cs.FLcited by 66

Not on the map. Why?

Abstract (arXiv)

We present a novel algorithm that uses exact learning and abstraction to extract a deterministic finite automaton describing the state dynamics of a given trained RNN. We do this using Angluin's L* algorithm as a learner and the trained RNN as an oracle. Our technique efficiently extracts accurate automata from trained RNNs, even when the state vectors are large and require fine differentiation.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 16; 2023: 10; 2024: 15; 2025: 6; 2026: 10.

66 papers.

Sort:

By area:

  1. 2021Thinking Like Transformerscited by 184
  2. 2022Neuro-Symbolic Language Modeling with Automaton-augmented Retrievalcited by 60
  3. 2023Learning Transformer Programscited by 41
  4. 2022Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifoldcited by 29
  5. 2023Interpretability Illusions in the Generalization of Simplified Modelscited by 25
  6. 2021Minimum Description Length Recurrent Neural Networkscited by 24
  7. 2024Training Neural Networks as Recognizers of Formal Languagescited by 24
  8. 2022SoK: Explainable Machine Learning for Computer Security Applicationscited by 20
  9. 2023Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensionscited by 20
  10. 2021BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networkscited by 17
  11. 2022Extracting Finite Automata from RNNs Using State Mergingcited by 17
  12. 2023Latent State Models of Training Dynamicscited by 16
38 more
  1. 2024Learning Useful Representations of Recurrent Neural Network Weight Matricescited by 15
  2. 2021Inferring Probabilistic Reward Machines from Non-Markovian Reward Processes for Reinforcement Learningcited by 13
  3. 2021Learning Description Logic Ontologies. Five Approaches. Where Do They Stand?cited by 12
  4. 2022Learning Interpretable Temporal Properties from Positive Examples Onlycited by 12
  5. 2022Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languagescited by 10
  6. 2023On the Computational Complexity and Formal Hierarchy of Second Order Recurrent Neural Networkscited by 8
  7. 2024DeepDFA: Automata Learning through Neural Probabilistic Relaxationscited by 8
  8. 2022Linguistically inspired roadmap for building biologically reliable protein language modelscited by 7
  9. 2023MLRegTest: A Benchmark for the Machine Learning of Regular Languagescited by 7
  10. 2023Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Taskscited by 7
  11. 2023DeepSeer: Interactive RNN Explanation and Debugging via State Abstractioncited by 6
  12. 2022ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniquescited by 5
  13. 2024Detecting Hidden Triggers: Mapping Non-Markov Reward Functions to Markovcited by 5
  14. 2023LUNA: A Model-Based Universal Analysis Framework for Large Language Modelscited by 4
  15. 2024Simulating Weighted Automata over Sequences and Trees with Transformerscited by 4
  16. 2025On the Statistical Query Complexity of Learning Semiautomata: a Random Walk Approachcited by 4
  17. 2021Extracting Weighted Automata for Approximate Minimization in Language Modellingcited by 3
  18. 2022Understanding Robust Generalization in Learning Regular Languagescited by 3
  19. 2024Stability Analysis of Various Symbolic Rule Extraction Methods from Recurrent Neural Networkcited by 3
  20. 2021Synthesizing Context-free Grammars from Recurrent Neural Networks (Extended Version)cited by 2
  21. 2022FlexFringe: Modeling Software Behavior by Learning Probabilistic Automatacited by 2
  22. 2022ImmunoLingo: Linguistics-based formalization of the antibody languagecited by 2
  23. 2022Verifying And Interpreting Neural Networks using Finite Automatacited by 2
  24. 2022State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictionscited by 2
  25. 2024L^*LM: Learning Automata from Examples using Natural Language Oraclescited by 2
  26. 2024Extracting Moore Machines from Transformers using Queries and Counterexamplescited by 2
  27. 2024Causal Abstraction in Model Interpretability: A Compact Surveycited by 2
  28. 2025A Constructive Framework for Nondeterministic Automata via Time-Shared, Depth-Unrolled Feedforward Networkscited by 2
  29. 2021On the Complexity of Learning Description Logic Ontologiescited by 1
  30. 2022Extracting Rules from Neural Networks with Partial Interpretationscited by 1
  31. 2022When are Local Queries Useful for Robust Learning?cited by 1
  32. 2023Learning Deterministic Finite Automata from Confidence Oraclescited by 1
  33. 2024Automata Extraction from Transformerscited by 1
  34. 2024Analyzing constrained LLM through PDFA-learningcited by 1
  35. 2024An L^* Algorithm for Deterministic Weighted Regular Languagescited by 1
  36. 2025RNN Generalization to Omega-Regular Languagescited by 1
  37. 2025Symbolic Feedforward Networks for Probabilistic Finite Automata: Exact Simulation and Learnabilitycited by 1
  38. 2025Extracting Robust Register Automata from Neural Networks over Data Sequencescited by 1

50 most cited of 66 All 66 (JSON)