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.
The erasure illusion: Stress-testing the general- ization of LLM forgetting evaluation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
PSALM is an LLM-as-a-judge framework with ten evaluators that operationalizes EU copyright doctrine to detect stylistic appropriation in fine-tuned LLMs beyond verbatim copying, applied to Llama 3.2 models on Dutch literary works.
Machine unlearning should be restricted to dataset-defined deletion achieving retraining equivalence, while other LLM tasks require separate terminology and evaluation baselines.
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.