Lifelong Normalization combined with ridge-regularized regression produces asymptotically orthogonal and bounded parameter updates that mitigate forgetting and collapse in lifelong model editing.
virtual samples
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
MixSD mixes tokens from the base model's expert and naive conditionals to create distribution-aligned supervision for knowledge injection, yielding better memorization-retention trade-offs than SFT across scales and benchmarks.
Forward replay replaces backward spreading in LLM parameter editing by optimizing the target hidden state at the first editing layer and propagating it forward, yielding more accurate layer-wise targets at the same computational cost.
SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER.
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.
citing papers explorer
-
More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
Lifelong Normalization combined with ridge-regularized regression produces asymptotically orthogonal and bounded parameter updates that mitigate forgetting and collapse in lifelong model editing.
-
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
MixSD mixes tokens from the base model's expert and naive conditionals to create distribution-aligned supervision for knowledge injection, yielding better memorization-retention trade-offs than SFT across scales and benchmarks.
-
From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
Forward replay replaces backward spreading in LLM parameter editing by optimizing the target hidden state at the first editing layer and propagating it forward, yielding more accurate layer-wise targets at the same computational cost.
-
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER.
-
Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.