pith. sign in

A concept-based explainability framework for large multimodal models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

roles

background 1

polarities

background 1

representative citing papers

A framework for analyzing concept representations in neural models

cs.CL · 2026-05-02 · unverdicted · novelty 7.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • A framework for analyzing concept representations in neural models cs.CL · 2026-05-02 · unverdicted · none · ref 2

    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.