Probe-geometry alignment erases cross-sequence memorization signatures in LLMs below chance using per-depth rank-one activation interventions with negligible impact on zero-shot capabilities.
Aggarwal, and Hui Liu
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Binding Subspace (BSU) attenuates intent-conditioned directions in autoregressive SLU models to reduce forced-prefix recoverability of unlearned intents.
citing papers explorer
-
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
Probe-geometry alignment erases cross-sequence memorization signatures in LLMs below chance using per-depth rank-one activation interventions with negligible impact on zero-shot capabilities.
-
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.