SOTAVerified

Model Editing

Papers

Showing 150 of 193 papers

TitleStatusHype
pyvene: A Library for Understanding and Improving PyTorch Models via InterventionsCode5
A Comprehensive Study of Knowledge Editing for Large Language ModelsCode5
Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and ValuesCode5
Neuron-Level Sequential Editing for Large Language ModelsCode3
Sparse Autoencoders Find Highly Interpretable Features in Language ModelsCode3
AlphaEdit: Null-Space Constrained Knowledge Editing for Language ModelsCode3
MEMORYLLM: Towards Self-Updatable Large Language ModelsCode3
Locating and Editing Factual Associations in GPTCode3
Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron AnalysisCode2
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)Code2
Model Editing as a Robust and Denoised variant of DPO: A Case Study on ToxicityCode2
UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language ModelsCode2
Decomposing and Editing Predictions by Modeling Model ComputationCode2
PMET: Precise Model Editing in a TransformerCode1
Cross-Lingual Consistency of Factual Knowledge in Multilingual Language ModelsCode1
On Mechanistic Knowledge Localization in Text-to-Image Generative ModelsCode1
ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at ScaleCode1
Model Editing by Standard Fine-TuningCode1
Model Editing Harms General Abilities of Large Language Models: Regularization to the RescueCode1
Rebuilding ROME : Resolving Model Collapse during Sequential Model EditingCode1
Massive Editing for Large Language Models via Meta LearningCode1
Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt LearningCode1
A Unified Framework for Model EditingCode1
Editing Massive Concepts in Text-to-Image Diffusion ModelsCode1
Aging with GRACE: Lifelong Model Editing with Discrete Key-Value AdaptorsCode1
Model Editing with Canonical ExamplesCode1
MemLLM: Finetuning LLMs to Use An Explicit Read-Write MemoryCode1
Learn From Model Beyond Fine-Tuning: A SurveyCode1
BadEdit: Backdooring large language models by model editingCode1
Perturbation-Restrained Sequential Model EditingCode1
Large Scale Knowledge WashingCode1
Learning to Model Editing ProcessesCode1
Memory-Based Model Editing at ScaleCode1
Detecting Edit Failures In Large Language Models: An Improved Specificity BenchmarkCode1
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language ModelsCode1
Interpreting and Controlling Vision Foundation Models via Text ExplanationsCode1
Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3Code1
Fast Model Editing at ScaleCode1
BiasEdit: Debiasing Stereotyped Language Models via Model EditingCode1
Editing Implicit Assumptions in Text-to-Image Diffusion ModelsCode1
Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language ModelsCode1
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction AttacksCode1
Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEditCode1
DUnE: Dataset for Unified EditingCode1
Locating and Editing Factual Associations in MambaCode1
History Matters: Temporal Knowledge Editing in Large Language ModelCode1
Editing Large Language Models: Problems, Methods, and OpportunitiesCode1
Evaluating the Ripple Effects of Knowledge Editing in Language ModelsCode1
Reinforced Lifelong Editing for Language ModelsCode1
Injecting Universal Jailbreak Backdoors into LLMs in MinutesCode1
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.