Knowledge Editing

Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning COLING 2025 Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models AAAI 2025 ReLearn: Unlearning via Learning for Large Language Models ACL 2025 RelEdit: Evaluating Conceptual Knowledge Editing in Language Models via Relational Reasoning ACL 2025 Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing EMNLP 2025 Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond ICLR 2025 Revealing and Mitigating Over-Attention in Knowledge Editing ICLR 2025 Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing EMNLP 2025 Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing ACL 2025 Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA EMNLP 2025 RuleEdit: Towards Rule-Level Knowledge Generalization to Mitigate Over-Editing in Large Language Models ACL 2025 Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching ACL 2025 SeqMMR: Sequential Model Merging and LLM Routing for Enhanced Batched Sequential Knowledge Editing ACL 2025 Serial Lifelong Editing via Mixture of Knowledge Experts ACL 2025 SetKE: Knowledge Editing for Knowledge Elements Overlap IJCAI 2025 STACKFEED: Structured Textual Actor-Critic Knowledge base editing with FEEDback EMNLP 2025 STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Models EMNLP 2025 StepKE: Stepwise Knowledge Editing for Multi-Hop Question Answering EMNLP 2025 Structure-aware Domain Knowledge Injection for Large Language Models ACL 2025 Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling NAACL 2025 SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering AAAI 2025 The Feasibility of Topic-Based Watermarking on Academic Peer Reviews IJCNLP 2025 The Knowledge Microscope: Features as Better Analytical Lenses than Neurons ACL 2025 The Mirage of Model Editing: Revisiting Evaluation in the Wild ACL 2025 Think and Recall: Layer-Level Prompting for Lifelong Model Editing EMNLP 2025