1
Can LLMs Be Constrained to the Past? Improving Knowledge Cutoff through Recall-Based Prompting
新研究用回忆式提示约束大模型知识截止时间，让回答更可靠，解决幻觉问题。
arXiv:2606.05804v1 Announce Type: new Abstract: Prompted knowledge cutoff instructs a large language model (LLM) to act as if information beyond a spe…