Causal Abstraction in Model Interpretability: A Compact Survey
Not on the map. Why?
Abstract (arXiv)
The pursuit of interpretable artificial intelligence has led to significant advancements in the development of methods that aim to explain the decision-making processes of complex models, such as deep learning systems. Among these methods, causal abstraction stands out as a theoretical framework that provides a principled approach to understanding and explaining the causal mechanisms underlying model behavior. This survey paper delves into the realm of causal abstraction, examining its theoretical foundations, practical applications, and implications for the field of model interpretability.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 26 references that are in the map. First posted on arXiv 26 Oct 2024.
Builds on
20 of 26 references.
References · 20
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
- 2021Causal Abstractions of Neural Networkscited by 401
- 2014A Tutorial on Principal Component Analysiscited by 139
- 2017Causal Consistency of Structural Equation Modelscited by 114
- 2018Abstracting Causal Modelscited by 104
- 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpacacited by 102
- 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
- 2022Polysemanticity and Capacity in Neural Networkscited by 74
- 2017Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamplescited by 66
- 2024SelfIE: Self-Interpretation of Large Language Model Embeddingscited by 63
8 more
- 2019Approximate Causal Abstractioncited by 62
- 2018Causal Inference by String Diagram Surgerycited by 23
- 2022Causal Abstraction with Soft Interventionscited by 23
- 2013A Probabilistic Calculus of Actionscited by 14
- 2022Abstraction between Structural Causal Models: A Review of Definitions and Propertiescited by 14
- 2022On the Equivalence of Causal Models: A Category-Theoretic Approachcited by 13
- 2023Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Taskscited by 7
- 2024Automata Extraction from Transformerscited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.