Geometric Unlearning suppresses specific knowledge in LLMs by projecting hidden planning states onto a low-rank safe geometry derived from minimal reference prompts.
Proceedings of the 41st International Conference on Machine Learning , 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 suppresses specific knowledge in LLMs by projecting hidden planning states onto a low-rank safe geometry derived from minimal reference prompts.