mlsanityData to 14 Oct 2026

Logically Consistent Language Models via Neuro-Symbolic Integration

arXiv 2409.13724 ↗First posted 9 Sep 2024cs.CL cs.AI cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting themselves when prompted to reason about relations between entities of the world. These problems are currently addressed with large scale fine-tuning or by delegating reasoning to external tools. In this work, we strive for a middle ground and introduce a loss based on neuro-symbolic reasoning that teaches an LLM to be logically consistent with an external set of facts and rules and improves self-consistency even when the LLM is fine-tuned on a limited set of facts. Our approach also allows to easily combine multiple logical constraints at once in a principled way, delivering LLMs that are more consistent w.r.t. all constraints and improve over several baselines w.r.t. a given constraint. Moreover, our method allows LLMs to extrapolate to unseen but semantically similar factual knowledge, represented in unseen datasets, more systematically.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 58 of its 75 references that are in the map. First posted on arXiv 9 Sep 2024.

Builds on

58 of 75 references.

References · 58

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2016Pointer Sentinel Mixture Modelscited by 3,096
  7. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  9. 2019Language Models as Knowledge Bases?cited by 1,936
  10. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  11. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 619
  12. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
38 more
  1. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 407
  2. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  3. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  4. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 270
  5. 2019Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Flycited by 243
  6. 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 242
  7. 2019Differentiation of Blackbox Combinatorial Solverscited by 226
  8. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 206
  9. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 196
  10. 2019CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Textcited by 162
  11. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
  12. 2022A Review on Language Models as Knowledge Basescited by 157
  13. 2023Factuality Challenges in the Era of Large Language Modelscited by 126
  14. 2021Truthful AI: Developing and governing AI that does not liecited by 113
  15. 2022Semantic Probabilistic Layers for Neuro-Symbolic Learningcited by 103
  16. 2020Analyzing Differentiable Fuzzy Logic Operatorscited by 101
  17. 2013A Differential Approach to Inference in Bayesian Networkscited by 93
  18. 2022On the Paradox of Learning to Reason from Datacited by 93
  19. 2024Is Cosine-Similarity of Embeddings Really About Similarity?cited by 89
  20. 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Basescited by 77
  21. 2020Coherent Hierarchical Multi-Label Classification Networkscited by 65
  22. 2019A Logic-Driven Framework for Consistency of Neural Modelscited by 64
  23. 2023RET-LLM: Towards a General Read-Write Memory for Large Language Modelscited by 64
  24. 2023Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcutscited by 63
  25. 2021BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Beliefcited by 57
  26. 2023FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answeringcited by 51
  27. 2023Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statementscited by 44
  28. 2021General-Purpose Question-Answering with Macawcited by 40
  29. 2022Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inferencecited by 40
  30. 2023Consistency Analysis of ChatGPTcited by 37
  31. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 37
  32. 2024MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memorycited by 35
  33. 2022ROAD-R: The Autonomous Driving Dataset with Logical Requirementscited by 34
  34. 2020Efficient Generation of Structured Objects with Constrained Adversarial Networkscited by 27
  35. 2022Neuro-Symbolic Entropy Regularizationcited by 27
  36. 2018Can Neural Networks Understand Logical Entailment?cited by 24
  37. 2023A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraintscited by 22
  38. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 13; 2026: 16.

30 papers.

Sort:

By area:

  1. 2026Scaling Reasoning Efficiently via Relaxed On-Policy Distillationcited by 82
  2. 2025Empowering LLMs with Logical Reasoning: A Comprehensive Surveycited by 51
  3. 2025Towards Robust Legal Reasoning: Harnessing Logical LLMs in Lawcited by 30
  4. 2025Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraintscited by 18
  5. 2025On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representationscited by 18
  6. 2025SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoningcited by 16
  7. 2025If Concept Bottlenecks are the Question, are Foundation Models the Answer?cited by 15
  8. 2025Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approachcited by 14
  9. 2025Neurosymbolic Diffusion Modelscited by 13
  10. 2025Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoningcited by 9
  11. 2025Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?cited by 7
  12. 2026Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms?cited by 6
18 more
  1. 2024Understanding the Logic of Direct Preference Alignment through Logiccited by 5
  2. 2026To Neuro-Symbolic Classification and Beyond by Compiling Description Logic Ontologies to Probabilistic Circuitscited by 3
  3. 2026Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidthcited by 3
  4. 2025The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inferencecited by 2
  5. 2026Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotationscited by 2
  6. 2026Structured Decomposition for LLM Reasoning: Cross-Domain Validation and Semantic Web Integrationcited by 1
  7. 2026Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMscited by 1
  8. 2026Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistencycited by 1
  9. 2026From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Modelscited by 1
  10. 2026LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solverscited by 1
  11. 2025Causal Reasoning Favors Encoders: On The Limits of Decoder-Only Modelscited by 0
  12. 2025A Neuro-Symbolic Framework for Accountability in Public-Sector AIcited by 0
  13. 2026Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Taskscited by 0
  14. 2026Can VLMs Reason Robustly? A Neuro-Symbolic Investigationcited by 0
  15. 2026Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiabilitycited by 0
  16. 2026SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verificationcited by 0
  17. 2026Solving versus Verifying: Catching Contradictions in Tax Reasoning Systemscited by 0
  18. 2026Understanding as No-Arbitrage: Bounded Dutch Books as a Definition and Training Objective for Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Large Language Models through Neuro-Symbolic Integration and Ontological Reasoning
  2. 2024Towards Logically Consistent Language Models via Probabilistic Reasoning
  3. 2024Reliable Reasoning Beyond Natural Language
  4. 2026Logic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning
  5. 2026Stratified Consistency Distillation for Natural Language Formalization
  6. 2025Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
  7. 2024Logical Consistency of Large Language Models in Fact-checking
  8. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches