解决知识库中新出现表达式与动态实体的匹配问题，提升RAG准确性。
DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG
- 基于时间分段聚类与持续适应，动态追踪实体演变。
- 在动态实体链接和问答任务中显著优于现有方法。
- 适合需要实时更新知识的RAG系统开发者使用。
在语言持续演化的背景下，如何将新出现的语言表达与不断更新的知识库中的实体关联，仍是重大挑战。这一问题在检索增强生成（RAG）中尤为关键，因新表达式会导致相关文档无法被检索，进而引发生成幻觉。为此，我们提出一项新任务：将新兴提及解析至动态实体，并构建DynamicER基准。该基准包含动态实体提及解析与以实体为中心的知识密集型问答任务，分别评估实体链接能力与RAG模型对新表达的适应性。实验发现，当前实体链接模型难以将新表达与实体关联。因此，我们提出一种带持续适应的时间分段聚类方法，有效处理实体演化的时间动态性与新提及。大量实验表明，该方法优于现有基线，在使用解析后提及的问答任务中显著提升RAG性能。
原文摘要 · Abstract (English)
In the rapidly evolving landscape of language, resolving new linguistic expressions in continuously updating knowledge bases remains a formidable challenge. This challenge becomes critical in retrieval-augmented generation (RAG) with knowledge bases, as emerging expressions hinder the retrieval of relevant documents, leading to generator hallucinations. To address this issue, we introduce a novel task aimed at resolving emerging mentions to dynamic entities and present DynamicER benchmark. Our benchmark includes dynamic entity mention resolution and entity-centric knowledge-intensive QA task, evaluating entity linking and RAG model's adaptability to new expressions, respectively. We discovered that current entity linking models struggle to link these new expressions to entities. Therefore, we propose a temporal segmented clustering method with continual adaptation, effectively managing the temporal dynamics of evolving entities and emerging mentions. Extensive experiments demonstrate that our method outperforms existing baselines, enhancing RAG model performance on QA task with resolved mentions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。