mlsanityData to 7 Oct 2026

Compositional Generalization via Neural-Symbolic Stack Machines

arXiv 2008.06662 ↗First posted 15 Aug 2020cs.LG cs.AI stat.MLcited by 80

Not on the map. Why?

Abstract (arXiv)

Despite achieving tremendous success, existing deep learning models have exposed limitations in compositional generalization, the capability to learn compositional rules and apply them to unseen cases in a systematic manner. To tackle this issue, we propose the Neural-Symbolic Stack Machine (NeSS). It contains a neural network to generate traces, which are then executed by a symbolic stack machine enhanced with sequence manipulation operations. NeSS combines the expressive power of neural sequence models with the recursion supported by the symbolic stack machine. Without training supervision on execution traces, NeSS achieves 100% generalization performance in four domains: the SCAN benchmark of language-driven navigation tasks, the task of few-shot learning of compositional instructions, the compositional machine translation benchmark, and context-free grammar parsing tasks.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 22; 2023: 15; 2024: 7; 2025: 7; 2026: 4.

80 papers.

Sort:

By area:

  1. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  2. 2021The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformerscited by 117
  3. 2022Teaching Algorithmic Reasoning via In-context Learningcited by 111
  4. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  5. 2022Compositional Semantic Parsing with Large Language Modelscited by 95
  6. 2023Large Language Models can Learn Rulescited by 66
  7. 2021The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalizationcited by 62
  8. 2021Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representationscited by 55
  9. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  10. 2023How Do In-Context Examples Affect Compositional Generalization?cited by 51
  11. 2022Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsingcited by 50
  12. 2021Improving Compositional Generalization with Latent Structure and Data Augmentationcited by 46
38 more
  1. 2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38
  2. 2022Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Reviewcited by 37
  3. 2024Learning Iterative Reasoning through Energy Diffusioncited by 36
  4. 2021On Compositional Generalization of Neural Machine Translationcited by 34
  5. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  6. 2023Skills-in-Context Prompting: Unlocking Compositionality in Large Language Modelscited by 33
  7. 2021Learning Algebraic Recombination for Compositional Generalizationcited by 31
  8. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  9. 2021Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalizationcited by 29
  10. 2022Unobserved Local Structures Make Compositional Generalization Hardcited by 29
  11. 2021Learning Algebraic Representation for Systematic Generalization in Abstract Reasoningcited by 27
  12. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  13. 2023Neural-Logic Human-Object Interaction Detectioncited by 25
  14. 2022Revisiting the Compositional Generalization Abilities of Neural Sequence Modelscited by 20
  15. 2022General Intelligence Requires Rethinking Explorationcited by 20
  16. 2021ReaSCAN: Compositional Reasoning in Language Groundingcited by 19
  17. 2021ProTo: Program-Guided Transformer for Program-Guided Taskscited by 19
  18. 2022Annealed Training for Combinatorial Optimization on Graphscited by 17
  19. 2023ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesiscited by 17
  20. 2022SUBS: Subtree Substitution for Compositional Semantic Parsingcited by 16
  21. 2022Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignmentcited by 16
  22. 2023Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Modelscited by 16
  23. 2022TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understandingcited by 15
  24. 2021Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCANcited by 14
  25. 2021UnweaveNet: Unweaving Activity Storiescited by 14
  26. 2021Compositional Attention: Disentangling Search and Retrievalcited by 12
  27. 2022Neural-Symbolic Recursive Machine for Systematic Generalizationcited by 12
  28. 2022When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarkscited by 11
  29. 2022Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Modelscited by 10
  30. 2024Neuro-Symbolic AI: Explainability, Challenges, and Future Trendscited by 10
  31. 2021Learning Symbolic Rules for Reasoning in Quasi-Natural Languagecited by 9
  32. 2022Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluationcited by 8
  33. 2021Compositional Generalization for Natural Language Interfaces to Web APIscited by 7
  34. 2021A Critical Review of Inductive Logic Programming Techniques for Explainable AIcited by 7
  35. 2023MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretationscited by 7
  36. 2023Can LLM find the green circle? Investigation and Human-guided tool manipulation for compositional generalizationcited by 7
  37. 2024ALTA: Compiler-Based Analysis of Transformerscited by 7
  38. 2021A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semanticscited by 6

50 most cited of 80 All 80 (JSON)