mlsanityData to 7 Oct 2026

ULLER: A Unified Language for Learning and Reasoning

arXiv 2405.00532 ↗First posted 1 May 2024cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

The field of neuro-symbolic artificial intelligence (NeSy), which combines learning and reasoning, has recently experienced significant growth. There now are a wide variety of NeSy frameworks, each with its own specific language for expressing background knowledge and how to relate it to neural networks. This heterogeneity hinders accessibility for newcomers and makes comparing different NeSy frameworks challenging. We propose a unified language for NeSy, which we call ULLER, a Unified Language for LEarning and Reasoning. ULLER encompasses a wide variety of settings, while ensuring that knowledge described in it can be used in existing NeSy systems. ULLER has a neuro-symbolic first-order syntax for which we provide example semantics including classical, fuzzy, and probabilistic logics. We believe ULLER is a first step towards making NeSy research more accessible and comparable, paving the way for libraries that streamline training and evaluation across a multitude of semantics, knowledge bases, and NeSy systems.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 32 of its 58 references that are in the map. First posted on arXiv 1 May 2024.

Builds on

32 of 58 references.

References · 32

  1. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  2. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  3. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  4. 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 203
  5. 2020Logic Tensor Networkscited by 197
  6. 2015Gradient Estimation Using Stochastic Computation Graphscited by 120
  7. 2022Semantic Probabilistic Layers for Neuro-Symbolic Learningcited by 103
  8. 2020Analyzing Differentiable Fuzzy Logic Operatorscited by 100
  9. 2023NeurASP: Embracing Neural Networks into Answer Set Programmingcited by 92
  10. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  11. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  12. 2018An Introduction to Probabilistic Programmingcited by 62
20 more
  1. 2021DeepStochLog: Neural Stochastic Logic Programmingcited by 58
  2. 2022A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inferencecited by 50
  3. 2018DiCE: The Infinitely Differentiable Monte-Carlo Estimatorcited by 46
  4. 2018Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledgecited by 45
  5. 2022Deep Learning with Logical Constraintscited by 44
  6. 2022NeuPSL: Neural Probabilistic Soft Logiccited by 34
  7. 2016TensorLog: A Differentiable Deductive Databasecited by 29
  8. 2019Neural Markov Logic Networkscited by 27
  9. 2020On Robustness Metrics for Learning STL Taskscited by 27
  10. 2023Neural Probabilistic Logic Programming in Discrete-Continuous Domainscited by 24
  11. 2019A Boxology of Design Patterns for Hybrid Learning and Reasoning Systemscited by 20
  12. 2023Logic of Differentiable Logics: Towards a Uniform Semantics of DLcited by 15
  13. 2023Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trickcited by 13
  14. 2021Storchastic: A Framework for General Stochastic Automatic Differentiationcited by 11
  15. 2022Refining neural network predictions using background knowledgecited by 11
  16. 2021SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programmingcited by 8
  17. 2024Semirings for Probabilistic and Neuro-Symbolic Logic Programmingcited by 6
  18. 2022TAR: Neural Logical Reasoning across TBox and ABoxcited by 2
  19. 2022Differentiable Fuzzy ALC: A Neural-Symbolic Representation Language for Symbol Groundingcited by 1
  20. 2024IID Relaxation by Logical Expressivity: A Research Agenda for Fitting Logics to Neurosymbolic Requirementscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 4.

9 papers.

  1. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
  2. 2025Defining neurosymbolic AIcited by 7
  3. 2024Understanding the Logic of Direct Preference Alignment through Logiccited by 5
  4. 2025The DeepLog Neurosymbolic Machinecited by 3
  5. 2025A General Framework for Property-Driven Machine Learningcited by 1
  6. 2026DeepLog: A Software Framework for Modular Neurosymbolic AIcited by 1
  7. 2026Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Modelscited by 0
  8. 2026NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learningcited by 0
  9. 2026Think-Verify-Revise: Neuro-Symbolic Visual Reasoning with Vision-Language Models and Dynamic Logic Tensor Networkscited by 0