Task structure is identifiable across time steps and task-relevant representations are identifiable within steps in a nonparametric setting under sparsity regularization.
Identifiable deep generative models via sparse decoding.arXiv preprint arXiv:2110.10804
4 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
4
Pith papers citing it
2
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
Linear representations of high-level concepts in LLMs are formalized via counterfactuals in input and output spaces, unified under a causal inner product that enables consistent probing and steering.
Diverse dictionary learning identifies intersections, complements, and dependency structures of latent variables from data X = g(Z) up to indeterminacies, and full identifiability when structural diversity is sufficient.
Mechanistic independence criteria yield identifiability of latent subspaces under nonlinear mixing by focusing on action-based independence rather than latent distributions, with a hierarchy and graph-theoretic view of subspaces.
citing papers explorer
-
From Generalist to Specialist Representation
Task structure is identifiable across time steps and task-relevant representations are identifiable within steps in a nonparametric setting under sparsity regularization.
-
The Linear Representation Hypothesis and the Geometry of Large Language Models
Linear representations of high-level concepts in LLMs are formalized via counterfactuals in input and output spaces, unified under a causal inner product that enables consistent probing and steering.
-
Diverse Dictionary Learning
Diverse dictionary learning identifies intersections, complements, and dependency structures of latent variables from data X = g(Z) up to indeterminacies, and full identifiability when structural diversity is sufficient.
-
Mechanistic Independence: A Principle for Identifiable Disentangled Representations
Mechanistic independence criteria yield identifiability of latent subspaces under nonlinear mixing by focusing on action-based independence rather than latent distributions, with a hierarchy and graph-theoretic view of subspaces.