mlsanityData to 7 Oct 2026

Approximate Causal Abstraction

arXiv 1906.11583 ↗First posted 27 Jun 2019cs.AIcited by 62

Not on the map. Why?

Abstract (arXiv)

Scientific models describe natural phenomena at different levels of abstraction. Abstract descriptions can provide the basis for interventions on the system and explanation of observed phenomena at a level of granularity that is coarser than the most fundamental account of the system. Beckers and Halpern (2019), building on work of Rubenstein et al. (2017), developed an account of abstraction for causal models that is exact. Here we extend this account to the more realistic case where an abstract causal model offers only an approximation of the underlying system. We show how the resulting account handles the discrepancy that can arise between low- and high-level causal models of the same system, and in the process provide an account of how one causal model approximates another, a topic of independent interest. Finally, we extend the account of approximate abstractions to probabilistic causal models, indicating how and where uncertainty can enter into an approximate abstraction.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 10; 2023: 17; 2024: 12; 2025: 12; 2026: 6.

62 papers.

Sort:

  1. 2021Causal Abstractions of Neural Networkscited by 401
  2. 2023Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationscited by 197
  3. 2023Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretabilitycited by 194
  4. 2023Localizing Model Behavior with Path Patchingcited by 182
  5. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  6. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  7. 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpacacited by 102
  8. 2024RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representationscited by 77
  9. 2021Local Explanations via Necessity and Sufficiency: Unifying Theory and Practicecited by 45
  10. 2021Compositional Abstraction Error and a Category of Causal Modelscited by 32
  11. 2024Mechanistic?cited by 25
  12. 2022Causal Abstraction with Soft Interventionscited by 23
38 more
  1. 2022Causal Inference Through the Structural Causal Marginal Problemcited by 22
  2. 2023Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learningcited by 22
  3. 2023Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributionscited by 21
  4. 2021Causal Distillation for Language Modelscited by 19
  5. 2024A Philosophical Introduction to Language Models - Part II: The Way Forwardcited by 17
  6. 2024The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applicationscited by 17
  7. 2022Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Trainingcited by 16
  8. 2023Targeted Reduction of Causal Modelscited by 15
  9. 2022Abstraction between Structural Causal Models: A Review of Definitions and Propertiescited by 14
  10. 2022On the Equivalence of Causal Models: A Category-Theoretic Approachcited by 13
  11. 2023Causal Optimal Transport of Abstractionscited by 13
  12. 2024Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environmentcited by 12
  13. 2023Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractionscited by 11
  14. 2022Towards a Grounded Theory of Causation for Embodied AIcited by 9
  15. 2023A Measure-Theoretic Axiomatisation of Causalitycited by 8
  16. 2022FACT: Learning Governing Abstractions Behind Integer Sequencescited by 6
  17. 2023Quantifying Consistency and Information Loss for Causal Abstraction Learningcited by 6
  18. 2023Interventionally Consistent Surrogates for Agent-based Simulatorscited by 6
  19. 2025What is causal about causal models and representations?cited by 6
  20. 2025Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventionscited by 6
  21. 2023Meaningful Causal Aggregation and Paradoxical Confoundingcited by 5
  22. 2024Causally Abstracted Multi-armed Banditscited by 5
  23. 2024Causal Representation Learning in Temporal Data via Single-Parent Decodingcited by 5
  24. 2024The Causal Information Bottleneck and Optimal Causal Variable Abstractionscited by 4
  25. 2025Combining Causal Models for More Accurate Abstractions of Neural Networkscited by 4
  26. 2022Neural Information Squeezer for Causal Emergencecited by 3
  27. 2022Towards Computing an Optimal Abstraction for Structural Causal Modelscited by 3
  28. 2022Language Models Understand Us, Poorlycited by 3
  29. 2023Causal Entropy and Information Gain for Measuring Causal Controlcited by 3
  30. 2023Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studiescited by 3
  31. 2025Distributionally Robust Causal Abstractionscited by 3
  32. 2024Toward A Causal Framework for Modeling Perceptioncited by 2
  33. 2024Causal Abstraction in Model Interpretability: A Compact Surveycited by 2
  34. 2025Modeling Discrimination with Causal Abstractioncited by 2
  35. 2026Coarsening Causal DAG Modelscited by 2
  36. 2023Do Not Marginalize Mechanisms, Rather Consolidate!cited by 1
  37. 2024Intuitions of Compromise: Utilitarianism vs. Contractualismcited by 1
  38. 2024Factored space models: Towards causality between levels of abstractioncited by 1

50 most cited of 62 All 62 (JSON)