Geometric Unlearning suppresses specific knowledge in LLMs by projecting hidden planning states onto a low-rank safe geometry derived from minimal reference prompts.
A practical guide, 1st ed., Cham: Springer International Publishing , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
FedCRF fuses global and local semantics via federated learning, semantic graphs, and contrastive constraints to improve cross-domain recommendations in non-overlapping scenarios.
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.
-
Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
-
FedCRF: A Federated Cross-domain Recommendation Method with Semantic-driven Deep Knowledge Fusion
FedCRF fuses global and local semantics via federated learning, semantic graphs, and contrastive constraints to improve cross-domain recommendations in non-overlapping scenarios.