GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?

In the real world, knowledge is constantly evolving, which can render existing knowledge-based datasets outdated.This unreliability highlights the critical need for continuous updates to ensure both accuracy and relevance in knowledgeintensive tasks.To address this, we propose GrowOVER-QA and GrowOVER-Dialogue, dynamic open-domain QA and dialogue benchmarks that undergo a continuous cycle of updates, keeping pace with the rapid evolution of knowledge.Our research indicates that retrieval-augmented language models (RaLMs) struggle with knowledge that has not been trained on or recently updated.Consequently, we introduce a novel retrieval-interactive language model framework, where the language model evaluates and reflects on its answers for further re-retrieval.Our exhaustive experiments demonstrate that our training-free framework significantly improves upon existing methods, performing comparably to or even surpassing continuously trained language models.QA & Dialogue New : D1-Turn1 [153], D1-Turn2 [154] QA1.What is Lionel Messi's all-time rank in goals scored from direct free?Old A.