Event-level Knowledge Editing
This addresses the problem of keeping LLMs up-to-date with real-world knowledge changes for users relying on current information, though it is incremental as it builds on existing knowledge editing methods.
The paper introduces event-level knowledge editing as a new task to update large language models (LLMs) by editing new events, which improves efficiency by updating multiple entailed knowledge triplets per edit and completeness by considering event influences and future trends, evaluated on a benchmark of 1,515 event edits and over 16,000 questions.
Knowledge editing aims at updating knowledge of large language models (LLMs) to prevent them from becoming outdated. Existing work edits LLMs at the level of factual knowledge triplets. However, natural knowledge updates in the real world come from the occurrences of new events rather than direct changes in factual triplets. In this paper, we propose a new task setting: event-level knowledge editing, which directly edits new events into LLMs and improves over conventional triplet-level editing on (1) Efficiency. A single event edit leads to updates in multiple entailed knowledge triplets. (2) Completeness. Beyond updating factual knowledge, event-level editing also requires considering the event influences and updating LLMs' knowledge about future trends. We construct a high-quality event-level editing benchmark ELKEN, consisting of 1,515 event edits, 6,449 questions about factual knowledge, and 10,150 questions about future tendencies. We systematically evaluate the performance of various knowledge editing methods and LLMs on this benchmark. We find that ELKEN poses significant challenges to existing knowledge editing approaches. Our codes and dataset are publicly released to facilitate further research.