SOTAVerified

knowledge editing

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 175 papers

TitleStatusHype
In-Context Editing: Learning Knowledge from Self-Induced DistributionsCode2
Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance—0
MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation—0
Identifying Query-Relevant Neurons in Large Language Models for Long-Form TextsCode0
RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuningCode0
DIEKAE: Difference Injection for Efficient Knowledge Augmentation and Editing of Large Language ModelsCode0
Knowledge Editing in Language Models via Adapted Direct Preference Optimization—0
Time Sensitive Knowledge Editing through Efficient FinetuningCode0
Outdated Issue Aware Decoding for Reasoning Questions on Edited KnowledgeCode0
Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language ModelsCode0
Knowledge Circuits in Pretrained TransformersCode2
Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language ModelsCode1
Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top—0
Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited FactsCode1
Large Language Model Bias Mitigation from the Perspective of Knowledge Editing—0
Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt LearningCode1
Detecting Edited Knowledge in Language Models—0
TAXI: Evaluating Categorical Knowledge Editing for Language ModelsCode0
DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMsCode0
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language ModelsCode0
Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness—0
Multi-hop Question Answering under Temporal Knowledge Editing—0
Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs—0
Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question AnsweringCode1
General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing—0
Locating and Mitigating Gender Bias in Large Language Models—0
Detoxifying Large Language Models via Knowledge EditingCode0
Editing Knowledge Representation of Language Model via Rephrased Prefix Prompts—0
BadEdit: Backdooring large language models by model editingCode1
VLKEB: A Large Vision-Language Model Knowledge Editing BenchmarkCode2
Editing Conceptual Knowledge for Large Language ModelsCode0
AKEW: Assessing Knowledge Editing in the WildCode0
InstructEdit: Instruction-based Knowledge Editing for Large Language ModelsCode0
Stable Knowledge Editing in Large Language ModelsCode1
Event-level Knowledge EditingCode1
Learning to Edit: Aligning LLMs with Knowledge EditingCode1
Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language ModelsCode1
Empirical Study on Updating Key-Value Memories in Transformer Feed-forward LayersCode0
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing—0
EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries—0
WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge EditingCode0
Knowledge Editing on Black-box Large Language ModelsCode0
Neighboring Perturbations of Knowledge Editing on Large Language ModelsCode1
Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks—0
DeepEdit: Knowledge Editing as Decoding with ConstraintsCode1
Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models—0
See the Unseen: Better Context-Consistent Knowledge-Editing by Noises—0
A Comprehensive Study of Knowledge Editing for Large Language ModelsCode5
PokeMQA: Programmable knowledge editing for Multi-hop Question AnsweringCode1
Retrieval-augmented Multilingual Knowledge EditingCode1
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.