A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
Representation biases: will we achieve com- plete understanding by analyzing represen- tations?
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Representational alignment varies monotonically with SNR and non-monotonically with sample size (minimized near interpolation threshold) across linear and nonlinear networks, and is decoupled from generalization error.
The paper formalizes homogenization in LLMs as a loss of deviance and core entropy, and proposes xeno-reproduction—a structure-aware diversity-pursuit objective—with a proof that diversity and fairness trade off.
Stimulus symmetries render many neural representations functionally equivalent yet produce qualitatively different RSMs, including drifting ones from SGD or regularization in image-encoding networks.
citing papers explorer
-
A framework for analyzing concept representations in neural models
A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
-
Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks
Representational alignment varies monotonically with SNR and non-monotonically with sample size (minimized near interpolation threshold) across linear and nonlinear networks, and is decoupled from generalization error.
-
The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety
The paper formalizes homogenization in LLMs as a loss of deviance and core entropy, and proposes xeno-reproduction—a structure-aware diversity-pursuit objective—with a proof that diversity and fairness trade off.
-
Stimulus symmetries can confound representational similarity analyses
Stimulus symmetries render many neural representations functionally equivalent yet produce qualitatively different RSMs, including drifting ones from SGD or regularization in image-encoding networks.