English
Related papers

Related papers: The Non-Linear Representation Dilemma: Is Causal A…

200 papers

Causal abstraction provides a theoretical foundation for mechanistic interpretability, the field concerned with providing intelligible algorithms that are faithful simplifications of the known, but opaque low-level details of black box AI…

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

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,…

Machine Learning · Computer Science 2024-10-29 Yihao Zhang

Explanations of cognitive behavior often appeal to computations over representations. What does it take for a system to implement a given computation over suitable representational vehicles within that system? We argue that the language of…

Machine Learning · Computer Science 2025-08-18 Atticus Geiger , Jacqueline Harding , Thomas Icard

The study of causal abstractions bridges two integral components of human intelligence: the ability to determine cause and effect, and the ability to interpret complex patterns into abstract concepts. Formally, causal abstraction frameworks…

Machine Learning · Computer Science 2025-09-29 Kevin Xia , Elias Bareinboim

Causal abstraction is a promising theoretical framework for explainable artificial intelligence that defines when an interpretable high-level causal model is a faithful simplification of a low-level deep learning system. However, existing…

Artificial Intelligence · Computer Science 2024-02-23 Atticus Geiger , Zhengxuan Wu , Christopher Potts , Thomas Icard , Noah D. Goodman

Abstracting from a low level to a more explanatory high level of description, and ideally while preserving causal structure, is fundamental to scientific practice, to causal inference problems, and to robust, efficient and interpretable AI.…

Logic in Computer Science · Computer Science 2026-02-19 Robin Lorenz , Sean Tull

The need for modelling causal knowledge at different levels of granularity arises in several settings. Causal Abstraction provides a framework for formalizing this problem by relating two Structural Causal Models at different levels of…

Machine Learning · Computer Science 2024-06-04 Riccardo Massidda , Sara Magliacane , Davide Bacciu

The abilities of humans to understand the world in terms of cause and effect relationships, as well as to compress information into abstract concepts, are two hallmark features of human intelligence. These two topics have been studied in…

Machine Learning · Computer Science 2024-02-26 Kevin Xia , Elias Bareinboim

Machine learning models have had discernible achievements in a myriad of applications. However, most of these models are black-boxes, and it is obscure how the decisions are made by them. This makes the models unreliable and untrustworthy.…

Machine Learning · Computer Science 2020-03-23 Raha Moraffah , Mansooreh Karami , Ruocheng Guo , Adrienne Raglin , Huan Liu

Causal abstraction provides a theory describing how several causal models can represent the same system at different levels of detail. Existing theoretical proposals limit the analysis of abstract models to "hard" interventions fixing…

Artificial Intelligence · Computer Science 2022-11-23 Riccardo Massidda , Atticus Geiger , Thomas Icard , Davide Bacciu

Understanding the predictions made by deep learning models remains a central challenge, especially in high-stakes applications. A promising approach is to equip models with the ability to answer counterfactual questions -- hypothetical…

Machine Learning · Computer Science 2025-10-28 Inwoo Hwang , Yushu Pan , Elias Bareinboim

Neural networks are hypothesized to implement interpretable causal mechanisms, yet verifying this requires finding a causal abstraction -- a simpler, high-level Structural Causal Model (SCM) faithful to the network under interventions.…

Machine Learning · Computer Science 2026-03-02 Amir Asiaee

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,…

Artificial Intelligence · Computer Science 2019-07-11 Sander Beckers , Joseph Y. Halpern

We present a categorical framework for relating causal models that represent the same system at different levels of abstraction. We define a causal abstraction as natural transformations between appropriate Markov functors, which concisely…

Machine Learning · Statistics 2025-10-07 Markus Englberger , Devendra Singh Dhami

Despite the recent success of neural network models in mimicking animal performance on visual perceptual tasks, critics worry that these models fail to illuminate brain function. We take it that a central approach to explanation in systems…

Neurons and Cognition · Quantitative Biology 2021-04-13 Rosa Cao , Daniel Yamins

Identifying the effect of a treatment from observational data typically requires assuming a fully specified causal diagram. However, such diagrams are rarely known in practice, especially in complex or high-dimensional settings. To overcome…

Artificial Intelligence · Computer Science 2025-07-09 Clément Yvernes , Emilie Devijver , Marianne Clausel , Eric Gaussier

Abstraction is a powerful idea widely used in science, to model, reason and explain the behavior of systems in a more tractable search space, by omitting irrelevant details. While notions of abstraction have matured for deterministic…

Artificial Intelligence · Computer Science 2020-01-14 Vaishak Belle

Structural analysis methods (e.g., probing and feature attribution) are increasingly important tools for neural network analysis. We propose a new structural analysis method grounded in a formal theory of causal abstraction that provides…

Artificial Intelligence · Computer Science 2021-10-28 Atticus Geiger , Hanson Lu , Thomas Icard , Christopher Potts

We provide explicit, finite-sample guarantees for learning causal representations from data with a sublinear number of environments. Causal representation learning seeks to provide a rigourous foundation for the general representation…

Machine Learning · Statistics 2026-03-30 Inbeom Lee , Tongtong Jin , Bryon Aragam
‹ Prev 1 2 3 10 Next ›