CLaRE quantifies representational entanglement in LLMs using single-layer forward activations to predict editing ripple effects, reporting 62.2% higher Spearman correlation than baselines while using 2.74x less time and 2.85x less GPU memory.
knowledge circuits
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
unclear 1representative 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
-
CLaRE-ty Amid Chaos: Quantifying Representational Entanglement to Predict Ripple Effects in LLM Editing
CLaRE quantifies representational entanglement in LLMs using single-layer forward activations to predict editing ripple effects, reporting 62.2% higher Spearman correlation than baselines while using 2.74x less time and 2.85x less GPU memory.
-
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.