Aligning Language Models with Real-time Knowledge Editing

arXiv:2508.01302v3 Announce Type: replace Abstract: Knowledge editing aims to modify outdated knowledge in language models efficiently while retaining their original capabilities. Mainstream datasets for knowledge editing are predominantly static and fail to keep in pace with the evolving real-world knowledge. In this work, we introduce CRAFT, an ever-evolving real-world dataset for knowledge editing. It evaluates models on temporal locality, common-sense locality, composite portability and alias portability, providing a comprehensive and challenging evaluation for knowledge editing, on which previous methods hardly achieve balanced performance. Towards flexible real-time knowledge editing, we propose KEDAS, a novel paradigm of knowledge editing alignment featuring diverse edit augmentation and self-adaptive post-alignment inference, exhibiting significant performance gain on both CRAFT and traditional datasets compared to previous methods. We hope this work may serve as a catalyst for shifting the focus of knowledge editing from static update to dynamic evolution.

Related

• From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
• Hallucination Detection and Evaluation of Large Language Model
• Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Source: arXiv cs.CL | 2026-04-21