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.
Proceedings of the 62nd
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2roles
extension 1polarities
extend 1representative citing papers
Language models employ a highly localized shared mechanism for filler-gap dependencies but no unified mechanism for NPI licensing, and activation patching generalizes better than supervised alignment search.
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.
-
Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models
Language models employ a highly localized shared mechanism for filler-gap dependencies but no unified mechanism for NPI licensing, and activation patching generalizes better than supervised alignment search.