Geometric Unlearning distills a low-rank safe subspace from reference prompts and applies projection-based alignment on synthetic anchors to suppress target content while preserving non-target utility.
Proceedings of the 31st International Conference on Computational Linguistics , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure
Geometric Unlearning distills a low-rank safe subspace from reference prompts and applies projection-based alignment on synthetic anchors to suppress target content while preserving non-target utility.