mlsanityData to 14 Oct 2026

Scallop: A Language for Neurosymbolic Programming

arXiv 2304.04812 ↗First posted 10 Apr 2023cs.PL cs.AI cs.LGcited by 63

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

We present Scallop, a language which combines the benefits of deep learning and logical reasoning. Scallop enables users to write a wide range of neurosymbolic applications and train them in a data- and compute-efficient manner. It achieves these goals through three key features: 1) a flexible symbolic representation that is based on the relational data model; 2) a declarative logic programming language that is based on Datalog and supports recursion, aggregation, and negation; and 3) a framework for automatic and efficient differentiable reasoning that is based on the theory of provenance semirings. We evaluate Scallop on a suite of eight neurosymbolic applications from the literature. Our evaluation demonstrates that Scallop is capable of expressing algorithmic reasoning in diverse and challenging AI tasks, provides a succinct interface for machine learning programmers to integrate logical domain knowledge, and yields solutions that are comparable or superior to state-of-the-art models in terms of accuracy. Furthermore, Scallop's solutions outperform these models in aspects such as runtime and data efficiency, interpretability, and generalizability.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 41 of its 84 references that are in the map. First posted on arXiv 10 Apr 2023.

Builds on

41 of 84 references.

References · 41

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2017Graph Attention Networkscited by 8,923
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  8. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  9. 2015Fast R-CNNcited by 2,933
  10. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  11. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  12. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
29 more
  1. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  2. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  3. 2015Automatic differentiation in machine learning: a surveycited by 855
  4. 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 700
  5. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 669
  6. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 664
  7. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  8. 2018Pyro: Deep Universal Probabilistic Programmingcited by 380
  9. 2015Neural Module Networkscited by 376
  10. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 372
  11. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  12. 2018Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understandingcited by 304
  13. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 270
  14. 2022Binding Language Models in Symbolic Languagescited by 228
  15. 2019SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solvercited by 173
  16. 2019CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Textcited by 162
  17. 2022How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projectionscited by 122
  18. 2022What Makes Convolutional Models Great on Long Sequence Modeling?cited by 87
  19. 2020Inductive logic programming at 30: a new introductioncited by 85
  20. 2018An Introduction to Probabilistic Programmingcited by 63
  21. 2020Learning Reasoning Strategies in End-to-End Differentiable Provingcited by 60
  22. 2020Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoningcited by 58
  23. 2021Inductive logic programming at 30cited by 47
  24. 2020Learning Differentiable Programs with Admissible Neural Heuristicscited by 32
  25. 2019Synthesizing Datalog Programs Using Numerical Relaxationcited by 23
  26. 2022MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENerationcited by 20
  27. 2017TensorLog: Deep Learning Meets Probabilistic DBscited by 11
  28. 2021Web Question Answering with Neurosymbolic Program Synthesiscited by 11
  29. 2021Convergence of Datalog over (Pre-) Semiringscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 11; 2025: 20; 2026: 28.

63 papers.

Sort:

By area:

  1. 2024Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoningcited by 19
  2. 2024KLay: Accelerating Arithmetic Circuits for Neurosymbolic AIcited by 16
  3. 2023Natural Language Embedded Programs for Hybrid Language Symbolic Reasoningcited by 15
  4. 2023LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervisioncited by 13
  5. 2025Neurosymbolic Diffusion Modelscited by 13
  6. 2023Exploiting Code Symmetries for Learning Program Semanticscited by 10
  7. 2025Defining neurosymbolic AIcited by 8
  8. 2023Teaching Probabilistic Logical Reasoning to Transformerscited by 7
  9. 2024Data-Efficient Learning with Neural Programscited by 7
  10. 2024Relational Programming with Foundation Modelscited by 7
  11. 2024Formal Explanations for Neuro-Symbolic AIcited by 6
  12. 2025Neural Probabilistic Circuits: Enabling Compositional and Interpretable Predictions through Logical Reasoningcited by 6
38 more
  1. 2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generationcited by 6
  2. 2024FaccAID: A Transformer Model for Neuro-Symbolic Facade Reconstructioncited by 5
  3. 2024Dolphin: A Programmable Framework for Scalable Neurosymbolic Learningcited by 5
  4. 2024Understanding the Logic of Direct Preference Alignment through Logiccited by 5
  5. 2025NeuroStrata: Harnessing Neurosymbolic Paradigms for Improved Design, Testability, and Verifiability of Autonomous CPScited by 5
  6. 2025LogicCBMs: Logic-Enhanced Concept-Based Learningcited by 5
  7. 2025Lobster: A GPU-Accelerated Framework for Neurosymbolic Programmingcited by 4
  8. 2026Theory-Scale Auto-Formalization of Logics for Computer Sciencecited by 4
  9. 2024MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programmingcited by 3
  10. 2025A Learnability Analysis on Neuro-Symbolic Learningcited by 3
  11. 2025Modal Logic Neural Networkscited by 3
  12. 2026To Neuro-Symbolic Classification and Beyond by Compiling Description Logic Ontologies to Probabilistic Circuitscited by 3
  13. 2024Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategiescited by 2
  14. 2025A Neuro-Symbolic Framework for Sequence Classification with Relational and Temporal Knowledgecited by 2
  15. 2025Neuro-Symbolic Frameworks: Conceptual Characterization and Empirical Comparative Analysiscited by 2
  16. 2025Compiling to linear neuronscited by 2
  17. 2026The Neural Compiler: Program-to-Network Translation for Hybrid Scientific Machine Learningcited by 2
  18. 2026Efficient and Sound Probabilistic Verification for AI Agentscited by 2
  19. 2026Does the Proof Prove It That Way? Faithful Formalization of Elements Proofscited by 2
  20. 2024Symbol Correctness in Deep Neural Networks Containing Symbolic Layerscited by 1
  21. 2025Hierarchical Neuro-Symbolic Decision Transformercited by 1
  22. 2025CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learningcited by 1
  23. 2025Curriculum Abductive Learningcited by 1
  24. 2025Augmented Vision-Language Models: A Systematic Reviewcited by 1
  25. 2025Multi-Model Synthetic Training for Mission-Critical Small Language Modelscited by 1
  26. 2025Neurosymbolic Inference On Foundation Models For Remote Sensing Text-to-image Retrieval With Complex Queriescited by 1
  27. 2026Constraint-Aware Neurosymbolic Uncertainty Quantification with Bayesian Deep Learning for Scientific Discoverycited by 1
  28. 2026On Improving Neurosymbolic Learning by Exploiting the Representation Spacecited by 1
  29. 2026Differentiable Modal Logic for Multi-Agent Diagnosis, Orchestration and Communicationcited by 1
  30. 20266.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First Instantiationcited by 1
  31. 2026From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Modelscited by 1
  32. 2025Compiling to recurrent neuronscited by 0
  33. 2025Prompt Less, Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineeringcited by 0
  34. 2026REASON: Accelerating Probabilistic Logical Reasoning for Scalable Neuro-Symbolic Intelligencecited by 0
  35. 2026Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Taskscited by 0
  36. 2026How Psychological Learning Paradigms Shaped and Constrained Artificial Intelligencecited by 0
  37. 2026AS2 -- Attention-Based Soft Answer Sets: An End-to-End Differentiable Neuro-Soft-Symbolic Reasoning Architecturecited by 0
  38. 2026THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecturecited by 0

50 most cited of 63 All 63 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
  2. 2025Current Practices for Building LLM-Powered Reasoning Tools Are Ad Hoc -- and We Can Do Better
  3. 2025On the Promise for Assurance of Differentiable Neurosymbolic Reasoning Paradigms
  4. 2026The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning
  5. 2026Forethought: Verifiable Reasoning from Neurosymbolic Primitive Programming
  6. 2025Reasoning in Neurosymbolic AI
  7. 2025A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning
  8. 2025Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI