SOTAVerified

Model Editing

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–193 of 193 papers

TitleStatusHype
Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation PatchingCode0
Long-form evaluation of model editingCode0
LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model EditingCode0
Learning Where to Edit Vision TransformersCode0
Resolving Lexical Bias in Edit Scoping with Projector Editor NetworksCode0
The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models CollapseCode0
MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRACode0
Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language ModelsCode0
Understanding the Collapse of LLMs in Model EditingCode0
Editing Factual Knowledge and Explanatory Ability of Medical Large Language ModelsCode0
Language Anisotropic Cross-Lingual Model EditingCode0
On the Robustness of Editing Large Language ModelsCode0
Cross-lingual Editing in Multilingual Language ModelsCode0
Unveiling Concept Attribution in Diffusion ModelsCode0
Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMsCode0
Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model EditingCode0
Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or HarmCode0
Model Editing at Scale leads to Gradual and Catastrophic ForgettingCode0
Editing Common Sense in TransformersCode0
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddingsCode0
How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queriesCode0
What does the Knowledge Neuron Thesis Have to do with Knowledge?Code0
Model Editing for LLMs4Code: How Far are We?Code0
Gradient Rewiring for Editable Graph Neural Network TrainingCode0
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language ModelsCode0
Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?Code0
Scalable Model Editing via Customized Expert NetworksCode0
Consecutive Batch Model Editing with HooK LayersCode0
UniErase: Unlearning Token as a Universal Erasure Primitive for Language ModelsCode0
Concept-ROT: Poisoning Concepts in Large Language Models with Model EditingCode0
NAMET: Robust Massive Model Editing via Noise-Aware Memory OptimizationCode0
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image ClassificationCode0
Should We Really Edit Language Models? On the Evaluation of Edited Language ModelsCode0
CoME: An Unlearning-based Approach to Conflict-free Model EditingCode0
"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language ModelsCode0
Can We Edit Multimodal Large Language Models?Code0
Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampeningCode0
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed ModelsCode0
ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRACode0
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language ModelsCode0
Drop Dropout on Single-Epoch Language Model PretrainingCode0
DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language ModelsCode0
Stealth edits to large language modelsCode0
Show:102550
← PrevPage 4 of 4Next →

No leaderboard results yet.