SOTAVerified

Model Editing

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 126–150 of 193 papers

TitleStatusHype
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)Code2
Towards Uncovering How Large Language Model Works: An Explainability Perspective—0
The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models CollapseCode0
Long-form evaluation of model editingCode0
Rethinking Machine Unlearning for Large Language Models—0
Model Editing with Canonical ExamplesCode1
On the Robustness of Editing Large Language ModelsCode0
MEMORYLLM: Towards Self-Updatable Large Language ModelsCode3
Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampeningCode0
Continual Learning for Large Language Models: A Survey—0
Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks—0
SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding AlteringCode0
From Understanding to Utilization: A Survey on Explainability for Large Language Models—0
Cross-lingual Editing in Multilingual Language ModelsCode0
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language ModelsCode0
Model Editing at Scale leads to Gradual and Catastrophic ForgettingCode0
Editing Arbitrary Propositions in LLMs without Subject Labels—0
Model Editing Harms General Abilities of Large Language Models: Regularization to the RescueCode1
MPN: Leveraging Multilingual Patch Neuron for Cross-lingual Model Editing—0
Large Language Models Relearn Removed ConceptsCode1
A Comprehensive Study of Knowledge Editing for Large Language ModelsCode5
MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRACode0
History Matters: Temporal Knowledge Editing in Large Language ModelCode1
Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation—0
DemoCaricature: Democratising Caricature Generation with a Rough Sketch—0
Show:102550
← PrevPage 6 of 8Next →

No leaderboard results yet.