mlsanityData to 7 Oct 2026

Declarative Design of Neural Predicates in Neuro-Symbolic Systems

arXiv 2405.09521 ↗First posted 15 May 2024cs.AIcited by 1

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Neuro-symbolic systems (NeSy), which claim to combine the best of both learning and reasoning capabilities of artificial intelligence, are missing a core property of reasoning systems: Declarativeness. The lack of declarativeness is caused by the functional nature of neural predicates inherited from neural networks. We propose and implement a general framework for fully declarative neural predicates, which hence extends to fully declarative NeSy frameworks. We first show that the declarative extension preserves the learning and reasoning capabilities while being able to answer arbitrary queries while only being trained on a single query type.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 12 of its 24 references that are in the map. First posted on arXiv 15 May 2024.

Builds on

12 of 24 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming7 Feb

Other references · 11

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2019An Introduction to Variational Autoencoderscited by 997
  4. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  5. 2020Logic Tensor Networkscited by 197
  6. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  7. 2023NeurASP: Embracing Neural Networks into Answer Set Programmingcited by 92
  8. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  9. 2021DeepStochLog: Neural Stochastic Logic Programmingcited by 58
  10. 2020Generative Neurosymbolic Machinescited by 57
  11. 2023Neural Probabilistic Logic Programming in Discrete-Continuous Domainscited by 24

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Understanding the Logic of Direct Preference Alignment through Logiccited by 5

Similar, not cited

Close in wording, no citation either way

  1. 2022Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review
  2. 2026Differentiable Logic Programming to Mitigate Reasoning Shortcuts in Neurosymbolic Systems
  3. 2025A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning
  4. 2025Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI
  5. 2026Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era
  6. 2024The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning
  7. 2025A Scalable Approach to Probabilistic Neuro-Symbolic Robustness Verification
  8. 2024Neuro-symbolic Learning Yielding Logical Constraints