Knowledge Editing

AdaEdit: Advancing Continuous Knowledge Editing For Large Language Models ACL 2025 AI Knowledge Assist: An Automated Approach for the Creation of Knowledge Bases for Conversational AI Agents EMNLP 2025 Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering CVPR 2025 Automating Annotation Guideline Improvements using LLMs: A Case Study COLING 2025 Avoiding Copyright Infringement via Large Language Model Unlearning NAACL 2025 Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition EMNLP 2025 Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs ACML 2025 BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning ACL 2025 CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners EMNLP 2025 Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs EMNLP 2025 CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs ACL 2025 COMPKE: Complex Question Answering under Knowledge Editing ACL 2025 ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning ACL 2025 Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts ACL 2025 EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models EMNLP 2025 Eigenvoice Synthesis based on Model Editing for Speaker Generation Interspeech 2025 EIKEA:Enhancing In-Context Knowledge Editing by Agents ACML 2025 Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching EMNLP 2025 ESC: Erasing Space Concept for Knowledge Deletion CVPR 2025 Evaluating and Enhancing Large Language Models for Novelty Assessment in Scholarly Publications NAACL 2025 Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer Enhancement ACL 2025 Explore What LLM Does Not Know in Complex Question Answering AAAI 2025 FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge EMNLP 2025 Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models ACL 2025 Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts AAAI 2025