Cover Image

Combining Causal Models for More Accurate Abstractions of Neural Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pîslar, Theodora-Mara, Magliacane, Sara, Geiger, Atticus
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Causal Abstractions of Linear Structural Causal Models
by: Massidda, Riccardo, et al.
Published: (2024)

How Causal Abstraction Underpins Computational Explanation
by: Geiger, Atticus, et al.
Published: (2025)

Local Causal Discovery for Statistically Efficient Causal Inference
by: Schubert, Mátyás, et al.
Published: (2025)

SNAP: Sequential Non-Ancestor Pruning for Targeted Causal Effect Estimation With an Unknown Graph
by: Schubert, Mátyás, et al.
Published: (2025)

Neural Causal Abstractions
by: Xia, Kevin, et al.
Published: (2024)

Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small
by: Chaudhary, Maheep, et al.
Published: (2024)

Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
by: Csordás, Róbert, et al.
Published: (2024)

Towards the Reusability and Compositionality of Causal Representations
by: Talon, Davide, et al.
Published: (2024)

How Do Transformers Learn Variable Binding in Symbolic Programs?
by: Wu, Yiwei, et al.
Published: (2025)

Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing
by: Xu, Danru, et al.
Published: (2026)

Learning to Defer for Causal Discovery with Imperfect Experts
by: Clivio, Oscar, et al.
Published: (2025)

A Sparsity Principle for Partially Observable Causal Representation Learning
by: Xu, Danru, et al.
Published: (2024)

Learning Consistent Causal Abstraction Networks
by: D'Acunto, Gabriele, et al.
Published: (2026)

Distributionally Robust Causal Abstractions
by: Felekis, Yorgos, et al.
Published: (2025)

Multi-View Causal Representation Learning with Partial Observability
by: Yao, Dingling, et al.
Published: (2023)

Efficient Discovery of Approximate Causal Abstractions via Neural Mechanism Sparsification
by: Asiaee, Amir
Published: (2026)

PLOT: Progressive Localization via Optimal Transport in Neural Causal Abstraction
by: Chang, Jonathn, et al.
Published: (2026)

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
by: Puyin, Li, et al.
Published: (2026)

ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks
by: You, Haoran, et al.
Published: (2022)

Networks of Causal Abstractions: A Sheaf-theoretic Framework
by: D'Acunto, Gabriele, et al.
Published: (2025)

Graph Neural Network Causal Explanation via Neural Causal Models
by: Behnam, Arman, et al.
Published: (2024)

A Relational Inductive Bias for Dimensional Abstraction in Neural Networks
by: Campbell, Declan, et al.
Published: (2024)

Causal Abstraction Learning based on the Semantic Embedding Principle
by: D'Acunto, Gabriele, et al.
Published: (2025)

Automatically Finding Reward Model Biases
by: Wang, Atticus, et al.
Published: (2026)

Causal Abstraction in Model Interpretability: A Compact Survey
by: Zhang, Yihao
Published: (2024)

Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks
by: Cho, Wonyong, et al.
Published: (2026)

The Causal Information Bottleneck and Optimal Causal Variable Abstractions
by: Simoes, Francisco N. F. Q., et al.
Published: (2024)

ReFT: Representation Finetuning for Language Models
by: Wu, Zhengxuan, et al.
Published: (2024)

HyperSteer: Activation Steering at Scale with Hypernetworks
by: Sun, Jiuding, et al.
Published: (2025)

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
by: Boppana, Siddharth, et al.
Published: (2026)

A Model of Causal Explanation on Neural Networks for Tabular Data
by: Isozaki, Takashi, et al.
Published: (2025)

Causal Graph Neural Networks for Healthcare
by: Mesinovic, Munib, et al.
Published: (2025)

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
by: Geiger, Atticus, et al.
Published: (2023)

Accurate and Scalable Graph Neural Networks via Message Invariance
by: Shi, Zhihao, et al.
Published: (2025)

OLMA: One Loss for More Accurate Time Series Forecasting
by: Shi, Tianyi, et al.
Published: (2025)

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
by: Sun, Jiuding, et al.
Published: (2025)

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
by: Wu, Zhengxuan, et al.
Published: (2024)

Causally-Aware Spatio-Temporal Multi-Graph Convolution Network for Accurate and Reliable Traffic Prediction
by: Dong, Pingping, et al.
Published: (2024)

From Black-box to Causal-box: Towards Building More Interpretable Models
by: Hwang, Inwoo, et al.
Published: (2025)

Causal Graph Neural Networks for Wildfire Danger Prediction
by: Zhao, Shan, et al.
Published: (2024)