mlsanityData to 7 Oct 2026

An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks

arXiv 1709.10380 ↗First posted 29 Sep 2017cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

Rule extraction from black-box models is critical in domains that require model validation before implementation, as can be the case in credit scoring and medical diagnosis. Though already a challenging problem in statistical learning in general, the difficulty is even greater when highly non-linear, recursive models, such as recurrent neural networks (RNNs), are fit to data. Here, we study the extraction of rules from second-order recurrent neural networks trained to recognize the Tomita grammars. We show that production rules can be stably extracted from trained RNNs and that in certain cases the rules outperform the trained RNNs.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 5; 2023: 5; 2024: 3; 2025: 2; 2026: 1.

21 papers.

Sort:

  1. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  2. 2023Learning Transformer Programscited by 40
  3. 2021Minimum Description Length Recurrent Neural Networkscited by 23
  4. 2022Extracting Finite Automata from RNNs Using State Mergingcited by 17
  5. 2022Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languagescited by 10
  6. 2024DeepDFA: Automata Learning through Neural Probabilistic Relaxationscited by 8
  7. 2022Linguistically inspired roadmap for building biologically reliable protein language modelscited by 7
  8. 2023Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Taskscited by 7
  9. 2023Neurosymbolic AI and its Taxonomy: a surveycited by 6
  10. 2022ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniquescited by 5
  11. 2021Extracting Weighted Automata for Approximate Minimization in Language Modellingcited by 3
  12. 2021Self-Supervised Learning to Prove Equivalence Between Straight-Line Programs via Rewrite Rulescited by 3
9 more
  1. 2024Stability Analysis of Various Symbolic Rule Extraction Methods from Recurrent Neural Networkcited by 3
  2. 2021Proving Equivalence Between Complex Expressions Using Graph-to-Sequence Neural Modelscited by 2
  3. 2022State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictionscited by 2
  4. 2023Learning Deterministic Finite Automata from Confidence Oraclescited by 1
  5. 2024Analyzing constrained LLM through PDFA-learningcited by 1
  6. 2025Extracting Robust Register Automata from Neural Networks over Data Sequencescited by 1
  7. 2023On the Relationship Between RNN Hidden State Vectors and Semantic Ground Truthcited by 0
  8. 2025Learning Model Successorscited by 0
  9. 2026NeuroRule: Making Black-Box Neural Networks Explainable through Rule-set Evolutioncited by 0