mlsanityData to 7 Oct 2026

Direct and Indirect Effects

arXiv 1301.2300 ↗First posted 10 Jan 2013cs.AI stat.MEcited by 276

Not on the map. Why?

Abstract (arXiv)

The direct effect of one eventon another can be defined and measured byholding constant all intermediate variables between the two.Indirect effects present conceptual andpractical difficulties (in nonlinear models), because they cannot be isolated by holding certain variablesconstant. This paper shows a way of defining any path-specific effectthat does not invoke blocking the remainingpaths.This permits the assessment of a more naturaltype of direct and indirect effects, one thatis applicable in both linear and nonlinear models. The paper establishesconditions under which such assessments can be estimated consistentlyfrom experimental and nonexperimental data,and thus extends path-analytic techniques tononlinear and nonparametric models.

Key facts. Cited by 276 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jan 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 29; 2023: 47; 2024: 59; 2025: 62; 2026: 50.

276 papers.

Sort:

By area:

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  2. 2022Mass-Editing Memory in a Transformercited by 976
  3. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  4. 2024Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Modelscited by 412
  5. 2021Causal Abstractions of Neural Networkscited by 401
  6. 2023Towards Best Practices of Activation Patching in Language Models: Metrics and Methodscited by 328
  7. 2023Function Vectors in Large Language Modelscited by 292
  8. 2023Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationscited by 197
  9. 2023Localizing Model Behavior with Path Patchingcited by 182
  10. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 155
  11. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  12. 2021Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Modelscited by 127
38 more
  1. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  2. 2024Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoningcited by 108
  3. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  4. 2023Circuit Component Reuse Across Tasks in Transformer Language Modelscited by 105
  5. 2024Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristicscited by 94
  6. 2023A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysiscited by 88
  7. 2022Debiased Learning from Naturally Imbalanced Pseudo-Labelscited by 85
  8. 2024RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representationscited by 77
  9. 2023Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patchingcited by 75
  10. 2022A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Modelscited by 68
  11. 2023Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIPcited by 62
  12. 2024Knowledge Circuits in Pretrained Transformerscited by 60
  13. 2024Confidence Regulation Neurons in Language Modelscited by 57
  14. 2025Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languagescited by 57
  15. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  16. 2024Demystifying Verbatim Memorization in Large Language Modelscited by 55
  17. 2022Neural Causal Models for Counterfactual Identification and Estimationcited by 54
  18. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  19. 2021Agent Incentives: A Causal Perspectivecited by 51
  20. 2024Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmeticcited by 50
  21. 2024Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learningcited by 49
  22. 2025MIB: A Mechanistic Interpretability Benchmarkcited by 49
  23. 2024Understanding Information Storage and Transfer in Multi-modal Large Language Modelscited by 48
  24. 2024Interpreting and Improving Large Language Models in Arithmetic Calculationcited by 43
  25. 2021Human Trajectory Prediction via Counterfactual Analysiscited by 42
  26. 2022From Statistical to Causal Learningcited by 40
  27. 2024Monitoring Latent World States in Language Models with Propositional Probescited by 39
  28. 2021Personalized Counterfactual Fairness in Recommendationcited by 38
  29. 2021Nested Counterfactual Identification from Arbitrary Surrogate Experimentscited by 38
  30. 2022Causal Conceptions of Fairness and their Consequencescited by 38
  31. 2024Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinationscited by 38
  32. 2021Factual Consistency Evaluation for Text Summarization via Counterfactual Estimationcited by 37
  33. 2023Neuron-Level Knowledge Attribution in Large Language Modelscited by 37
  34. 2023SoK: Memorization in General-Purpose Large Language Modelscited by 36
  35. 2024Uncovering Overfitting in Large Language Model Editingcited by 36
  36. 2024Locating and Editing Factual Associations in Mambacited by 35
  37. 2025Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMscited by 35
  38. 2021Sparse Interventions in Language Models with Differentiable Maskingcited by 34

50 most cited of 276 All 276 (JSON)