TimeROME-DLM enables training-free knowledge editing in masked diffusion language models via temporal causal tracing and low-rank residual edit memory applied at inference time.
arXiv preprint arXiv:2401.07453 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ORE decouples semantic entanglement in LLM hidden states via orthogonal edit vectors and a gated non-linear head, improving batch knowledge editing performance including cross-lingual cases.
citing papers explorer
-
TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models
TimeROME-DLM enables training-free knowledge editing in masked diffusion language models via temporal causal tracing and low-rank residual edit memory applied at inference time.
-
Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs
ORE decouples semantic entanglement in LLM hidden states via orthogonal edit vectors and a gated non-linear head, improving batch knowledge editing performance including cross-lingual cases.