SOTAVerified

knowledge editing

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 175 papers

TitleStatusHype
One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models—0
Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts—0
Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models—0
Model Editing for LLMs4Code: How Far are We?Code0
Reasons and Solutions for the Decline in Model Performance after EditingCode0
Commonsense Knowledge Editing Based on Free-Text in LLMsCode0
Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing—0
Can Knowledge Editing Really Correct Hallucinations?Code1
EcomEdit: An Automated E-commerce Knowledge Editing Framework for Enhanced Product and Purchase Intention Understanding—0
Can We Reverse In-Context Knowledge Edits?—0
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization—0
O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing—0
Keys to Robust Edits: from Theoretical Insights to Practical Advances—0
CollabEdit: Towards Non-destructive Collaborative Knowledge EditingCode0
Uncovering Overfitting in Large Language Model Editing—0
Mitigating Gender Bias in Code Large Language Models via Model Editing—0
Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing—0
RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context LearningCode0
AlphaEdit: Null-Space Constrained Knowledge Editing for Language ModelsCode3
Precision Knowledge Editing: Enhancing Safety in Large Language Models—0
Towards Unified Multimodal Editing with Enhanced Knowledge CollaborationCode1
Identifying Knowledge Editing Types in Large Language ModelsCode0
"Why" Has the Least Side Effect on Model Editing—0
Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative CriterionCode0
MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language—0
From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs—0
StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models—0
OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing SystemCode1
CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMsCode0
Does Knowledge Localization Hold True? Surprising Differences Between Entity and Relation Perspectives in Language Models—0
LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environments—0
Retrieval-Augmented Instruction Tuning for Automated Process Engineering Calculations : A Tool-Chaining Problem-Solving Framework with Attributable Reflection—0
Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models—0
Towards Human-Level Understanding of Complex Process Engineering Schematics: A Pedagogical, Introspective Multi-Agent Framework for Open-Domain Question Answering—0
Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing—0
Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs—0
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language ModelsCode0
The Mechanics of Conceptual Interpretation in GPT Models: Interpretative Insights—0
Can Editing LLMs Inject Harm?Code1
Cross-Lingual Multi-Hop Knowledge Editing -- Benchmarks, Analysis and a Simple Contrastive Learning based Approach—0
Composable Interventions for Language ModelsCode1
CodeUpdateArena: Benchmarking Knowledge Editing on API UpdatesCode1
Why Does New Knowledge Create Messy Ripple Effects in LLMs?—0
BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning—0
How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?—0
Understanding Language Model Circuits through Knowledge Editing—0
Multilingual Knowledge Editing with Language-Agnostic Factual NeuronsCode0
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency—0
Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities—0
Retrieval Meets Reasoning: Dynamic In-Context Editing for Long-Text Understanding—0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.