model editing

CoME: An Unlearning-based Approach to Conflict-free Model Editing NAACL 2025 ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning ICLR 2025 Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing ICLR 2025 Constraining Sequential Model Editing with Editing Anchor Compression NAACL 2025 Context-Robust Knowledge Editing for Language Models ACL 2025 Contrastive Unlearning: A Contrastive Approach to Machine Unlearning IJCAI 2025 DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing ACL 2025 Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms EMNLP 2025 DocMEdit: Towards Document-Level Model Editing ACL 2025 Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models EMNLP 2025 Drop Dropout on Single Epoch Language Model Pretraining ACL 2025 EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models EMNLP 2025 Editing Memories Through Few Targeted Neurons AAAI 2025 Efficient Knowledge Editing via Minimal Precomputation ACL 2025 Efficient Model Editing with Task-Localized Sparse Fine-tuning ICLR 2025 Eigenvoice Synthesis based on Model Editing for Speaker Generation Interspeech 2025 ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA AAAI 2025 Erasing Undesirable Influence in Diffusion Models CVPR 2025 Exploiting Edited Large Language Models as General Scientific Optimizers NAACL 2025 Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification AAAI 2025 Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models CVPR 2025 HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks ACL 2025 In-Context Editing: Learning Knowledge from Self-Induced Distributions ICLR 2025 Initializing and Retrofitting Key-Value Adaptors for Traceable Model Editing ACL 2025 Injecting Universal Jailbreak Backdoors into LLMs in Minutes ICLR 2025