mlsanityData to 7 Oct 2026

A Logic-Driven Framework for Consistency of Neural Models

arXiv 1909.00126 ↗First posted 31 Aug 2019cs.AI cs.CL cs.LGcited by 64

Not on the map. Why?

Abstract (arXiv)

While neural models show remarkable accuracy on individual predictions, their internal beliefs can be inconsistent across examples. In this paper, we formalize such inconsistency as a generalization of prediction error. We propose a learning framework for constraining models using logic rules to regularize them away from inconsistency. Our framework can leverage both labeled and unlabeled examples and is directly compatible with off-the-shelf learning schemes without model redesign. We instantiate our framework on natural language inference, where experiments show that enforcing invariants stated in logic can help make the predictions of neural models both accurate and consistent.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 7; 2023: 15; 2024: 13; 2025: 11; 2026: 3.

64 papers.

Sort:

By area:

  1. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 361
  2. 2024Do Large Language Models Latently Perform Multi-Hop Reasoning?cited by 165
  3. 2023Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Modelscited by 117
  4. 2021BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Beliefcited by 56
  5. 2025Empowering LLMs with Logical Reasoning: A Comprehensive Surveycited by 51
  6. 2022Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inferencecited by 40
  7. 2022Entailer: Answering Questions with Faithful and Truthful Chains of Reasoningcited by 38
  8. 2023Consistency Analysis of ChatGPTcited by 37
  9. 2022Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoningcited by 32
  10. 2023Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChaincited by 31
  11. 2024Logically Consistent Language Models via Neuro-Symbolic Integrationcited by 30
  12. 2021Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understandingcited by 19
38 more
  1. 2023RECKONING: Reasoning through Dynamic Knowledge Encodingcited by 17
  2. 2023Separating form and meaning: Using self-consistency to quantify task understanding across multiple sensescited by 15
  3. 2023Language Models with Rationalitycited by 15
  4. 2024Logical Consistency of Large Language Models in Fact-checkingcited by 15
  5. 2025Consistency in Language Models: Current Landscape, Challenges, and Future Directionscited by 14
  6. 2021Extracting Event Temporal Relations via Hyperbolic Geometrycited by 13
  7. 2022Do language models have coherent mental models of everyday things?cited by 13
  8. 2022Entailment Graph Learning with Textual Entailment and Soft Transitivitycited by 11
  9. 2021Consistency Training with Virtual Adversarial Discrete Perturbationcited by 9
  10. 2021Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completioncited by 9
  11. 2021Learning Constraints and Descriptive Segmentation for Subevent Detectioncited by 9
  12. 2023GLUECons: A Generic Benchmark for Learning Under Constraintscited by 9
  13. 2021Learning with Instance Bundles for Reading Comprehensioncited by 8
  14. 2021Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Studycited by 8
  15. 2022Generalized Quantifiers as a Source of Error in Multilingual NLU Benchmarkscited by 8
  16. 2024From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verificationcited by 8
  17. 2021AI Descartes: Combining Data and Theory for Derivable Scientific Discoverycited by 7
  18. 2023Teaching Probabilistic Logical Reasoning to Transformerscited by 7
  19. 2024From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistencycited by 7
  20. 2021Paired Examples as Indirect Supervision in Latent Decision Modelscited by 6
  21. 2022Breakpoint Transformers for Modeling and Tracking Intermediate Beliefscited by 6
  22. 2021Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifierscited by 5
  23. 2024Hire Me or Not? Examining Language Model's Behavior with Occupation Attributescited by 5
  24. 2024SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Imagescited by 5
  25. 2024Understanding the Logic of Direct Preference Alignment through Logiccited by 5
  26. 2025The Need for Verification in AI-Driven Scientific Discoverycited by 5
  27. 2021Enriching a Model's Notion of Belief using a Persistent Memorycited by 4
  28. 2021Self-Correcting Neural Networks For Safe Classificationcited by 4
  29. 2023Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionarycited by 4
  30. 2024Promptly Predicting Structures: The Return of Inferencecited by 4
  31. 2025Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priorscited by 4
  32. 2021Image Classification with Consistent Supporting Evidencecited by 3
  33. 2023On Regularization and Inference with Label Constraintscited by 3
  34. 2024CONTESTS: a Framework for Consistency Testing of Span Probabilities in Language Modelscited by 3
  35. 2025LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrievalcited by 3
  36. 2025Found in Translation: Measuring Multilingual LLM Consistency as Simple as Translate then Evaluatecited by 3
  37. 2023The Integer Linear Programming Inference Cookbookcited by 2
  38. 2024Interpretable Multimodal Out-of-context Detection with Soft Logic Regularizationcited by 2

50 most cited of 64 All 64 (JSON)