mlsanityData to 14 Oct 2026

Neurosymbolic AI and its Taxonomy: a survey

arXiv 2305.08876 ↗First posted 12 May 2023cs.NE cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Neurosymbolic AI deals with models that combine symbolic processing, like classic AI, and neural networks, as it's a very established area. These models are emerging as an effort toward Artificial General Intelligence (AGI) by both exploring an alternative to just increasing datasets' and models' sizes and combining Learning over the data distribution, Reasoning on prior and learned knowledge, and by symbiotically using them. This survey investigates research papers in this area during recent years and brings classification and comparison between the presented models as well as applications.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 28 of its 61 references that are in the map. First posted on arXiv 12 May 2023.

Builds on

28 of 61 references.

References · 28

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  2. 2015Fast R-CNNcited by 2,933
  3. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  4. 2015Pointer Networkscited by 895
  5. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 372
  6. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  7. 2018TextWorld: A Learning Environment for Text-based Gamescited by 310
  8. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 232
  9. 2020Logic Tensor Networkscited by 199
  10. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 195
  11. 2016Language to Logical Form with Neural Attentioncited by 158
  12. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 151
16 more
  1. 2019Neural Logic Machinescited by 145
  2. 2020Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspectivecited by 95
  3. 2017Logic Tensor Networks for Semantic Image Interpretationcited by 92
  4. 2016Neuro-Symbolic Program Synthesiscited by 84
  5. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  6. 2020Generative Neurosymbolic Machinescited by 57
  7. 2020Leveraging Abstract Meaning Representation for Knowledge Base Question Answeringcited by 53
  8. 2018FNNC: Achieving Fairness through Neural Networkscited by 43
  9. 2020Fusing Physics-based and Deep Learning Models for Prognosticscited by 40
  10. 2021Foundations of Symbolic Languages for Model Interpretabilitycited by 26
  11. 2017An Empirical Evaluation of Rule Extraction from Recurrent Neural Networkscited by 21
  12. 2019Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination Patternscited by 14
  13. 2021LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linkingcited by 11
  14. 2021LOA: Logical Optimal Actions for Text-based Interaction Gamescited by 6
  15. 2020Neurosymbolic AI for Situated Language Understandingcited by 2
  16. 2021Logical Boltzmann Machinescited by 2

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 4.

6 papers.

  1. 2024A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligencecited by 10
  2. 2025A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectivescited by 5
  3. 2025CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMscited by 3
  4. 2024Multi-Excitation Projective Simulation with a Many-Body Physics Inspired Inductive Biascited by 2
  5. 2025Enhancing Symbolic Machine Learning by Subsymbolic Representationscited by 2
  6. 2025A Neuro-Symbolic Framework for Accountability in Public-Sector AIcited by 0