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.
” alexa, can you forget me?
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
UBD leverages ensemble uncertainty to estimate per-sample memorization and construct debiased targets for post-hoc correction or unlearning, yielding output distributions closer to uncontaminated models on MMLU-Pro and MATH-MCQA than baselines.
Binding Subspace (BSU) attenuates intent-conditioned directions in autoregressive SLU models to reduce forced-prefix recoverability of unlearned intents.
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.
-
Uncertainty-based Debiasing and Unlearning for Decontamination
UBD leverages ensemble uncertainty to estimate per-sample memorization and construct debiased targets for post-hoc correction or unlearning, yielding output distributions closer to uncontaminated models on MMLU-Pro and MATH-MCQA than baselines.
-
Selective Capability Unlearning in End-to-End Spoken Language Understanding
Binding Subspace (BSU) attenuates intent-conditioned directions in autoregressive SLU models to reduce forced-prefix recoverability of unlearned intents.