mlsanityData to 7 Oct 2026

Abstracting Causal Models

arXiv 1812.03789 ↗First posted 10 Dec 2018cs.AIcited by 104

Not on the map. Why?

Abstract (arXiv)

We consider a sequence of successively more restrictive definitions of abstraction for causal models, starting with a notion introduced by Rubenstein et al. (2017) called exact transformation that applies to probabilistic causal models, moving to a notion of uniform transformation that applies to deterministic causal models and does not allow differences to be hidden by the "right" choice of distribution, and then to abstraction, where the interventions of interest are determined by the map from low-level states to high-level states, and strong abstraction, which takes more seriously all potential interventions in a model, not just the allowed interventions. We show that procedures for combining micro-variables into macro-variables are instances of our notion of strong abstraction, as are all the examples considered by Rubenstein et al.

Key facts. Cited by 104 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 14; 2023: 18; 2024: 15; 2025: 25; 2026: 24.

104 papers.

Sort:

By area:

  1. 2021Causal Abstractions of Neural Networkscited by 401
  2. 2023Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretabilitycited by 194
  3. 2022Weakly supervised causal representation learningcited by 140
  4. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  5. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  6. 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpacacited by 102
  7. 2025The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?cited by 34
  8. 2022Causal Effect Identification in Cluster DAGscited by 33
  9. 2021Compositional Abstraction Error and a Category of Causal Modelscited by 32
  10. 2025Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?cited by 32
  11. 2024Unifying Causal Representation Learning with the Invariance Principlecited by 30
  12. 2022Causal Abstraction with Soft Interventionscited by 23
38 more
  1. 2021Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Modelscited by 22
  2. 2022Causal Inference Through the Structural Causal Marginal Problemcited by 22
  3. 2023Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learningcited by 22
  4. 2026Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behaviorcited by 22
  5. 2023Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributionscited by 21
  6. 2024Neural Causal Abstractionscited by 20
  7. 2021Causal Distillation for Language Modelscited by 19
  8. 2024The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applicationscited by 17
  9. 2022Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Trainingcited by 16
  10. 2022A Causal Analysis of Harmcited by 15
  11. 2023Targeted Reduction of Causal Modelscited by 15
  12. 2022Abstraction between Structural Causal Models: A Review of Definitions and Propertiescited by 14
  13. 2022On the Equivalence of Causal Models: A Category-Theoretic Approachcited by 13
  14. 2023Causal Optimal Transport of Abstractionscited by 13
  15. 2024Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neurosciencecited by 11
  16. 2025How Causal Abstraction Underpins Computational Explanationcited by 10
  17. 2025The Dead Salmons of AI Interpretabilitycited by 10
  18. 2022Towards a Grounded Theory of Causation for Embodied AIcited by 9
  19. 2024Learning Causal Abstractions of Linear Structural Causal Modelscited by 9
  20. 2025Causal Abstraction Learning based on the Semantic Embedding Principlecited by 9
  21. 2021Operationalizing Complex Causes: A Pragmatic View of Mediationcited by 8
  22. 2023A Measure-Theoretic Axiomatisation of Causalitycited by 8
  23. 2024Identifying Macro Conditional Independencies and Macro Total Effects in Summary Causal Graphs with Latent Confoundingcited by 8
  24. 2026Causality is Key for Interpretability Claims to Generalisecited by 8
  25. 2021Causal Modeling With Infinitely Many Variablescited by 7
  26. 2021Reasoning About Causal Models With Infinitely Many Variablescited by 7
  27. 2022Phenomenological Causalitycited by 7
  28. 2022FACT: Learning Governing Abstractions Behind Integer Sequencescited by 6
  29. 2023Quantifying Consistency and Information Loss for Causal Abstraction Learningcited by 6
  30. 2023Interventionally Consistent Surrogates for Agent-based Simulatorscited by 6
  31. 2024Aligning Graphical and Functional Causal Abstractionscited by 6
  32. 2025What is causal about causal models and representations?cited by 6
  33. 2025A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.icited by 6
  34. 2023Meaningful Causal Aggregation and Paradoxical Confoundingcited by 5
  35. 2024Causally Abstracted Multi-armed Banditscited by 5
  36. 2024The Causal Information Bottleneck and Optimal Causal Variable Abstractionscited by 4
  37. 2025Combining Causal Models for More Accurate Abstractions of Neural Networkscited by 4
  38. 2022Abstracting Noisy Robot Programscited by 3

50 most cited of 104 All 104 (JSON)