How Causal Abstraction Underpins Computational Explanation
read the original abstract
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 causality -- and specifically the theory of causal abstraction -- provides a fruitful lens on this topic. Drawing on current discussions in deep learning with artificial neural networks, we illustrate how classical themes in the philosophy of computation and cognition resurface in contemporary machine learning. We offer an account of computational implementation grounded in causal abstraction, and examine the role for representation in the resulting picture. We argue that these issues are most profitably explored in connection with generalization and prediction.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Localizing Anchoring Pathways in Language Models
Attribution methods localize anchoring signals in Qwen and Llama models; edge-level circuits transfer within a model but show sparse transfer from base to instruction-tuned variants.
-
You Can't Fight in Here! This is BBS!
Language models can provide scientific insights into human language beyond mere string statistics, and the language sciences should pursue a broader research program that integrates computational and theoretical approaches.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.