HiEdit uses hierarchical RL to dynamically pick knowledge-relevant layers for editing LLMs, improving performance over baselines while perturbing only half the layers per edit.
NeurIPS 2024
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
-
HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning
HiEdit uses hierarchical RL to dynamically pick knowledge-relevant layers for editing LLMs, improving performance over baselines while perturbing only half the layers per edit.