Skip to content
conftrace_
2025 CLeaR CLeaR 2025

Combining Causal Models for More Accurate Abstractions of Neural Networks

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Theodora-Mara Pîslar, Sara Magliacane, Atticus Geiger

Topics

Artificial Intelligence > Core AI > Causal Inference Artificial Intelligence > Core AI > Interpretability Deep Learning > Models > Large Language Models

Keywords

causal abstraction neural network faithfulness computational states high-level algorithms interchange intervention accuracy
Download PDF