Knowledge Editing

Initializing and Retrofitting Key-Value Adaptors for Traceable Model Editing ACL 2025 Intrinsic Test of Unlearning Using Parametric Knowledge Traces EMNLP 2025 Joint Knowledge Editing for Information Enrichment and Probability Promotion AAAI 2025 Keys to Robust Edits: From Theoretical Insights to Practical Advances ACL 2025 Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models ACL 2025 Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis IJCAI 2025 Knowledge Editing through Chain-of-Thought EMNLP 2025 Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering AAAI 2025 Knowledge Graph Unlearning with Schema COLING 2025 Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models AAAI 2025 LastingBench: Defend Benchmarks Against Knowledge Leakage EMNLP 2025 Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge EMNLP 2025 Learn and Unlearn: Addressing Misinformation in Multilingual LLMs EMNLP 2025 Lifelong Model Editing with Graph-Based External Memory ACL 2025 LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates ACL 2025 MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency ACL 2025 Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning ACL 2025 MEraser: An Effective Fingerprint Erasure Approach for Large Language Models ACL 2025 MicroEdit: Neuron-level Knowledge Disentanglement and Localization in Lifelong Model Editing EMNLP 2025 Model Merging for Knowledge Editing ACL 2025 Neuron-Level Sequential Editing for Large Language Models ACL 2025 NILE: Internal Consistency Alignment in Large Language Models EMNLP 2025 One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit ACL 2025 Parameter-Aware Contrastive Knowledge Editing: Tracing and Rectifying based on Critical Transmission Paths ACL 2025 Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models COLING 2025