DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG
This addresses a critical problem for RAG systems with knowledge bases by improving adaptability to new expressions, though it is incremental as it builds on existing entity linking and RAG frameworks.
The paper tackles the challenge of resolving emerging mentions to dynamic entities in retrieval-augmented generation (RAG) systems, where new linguistic expressions hinder document retrieval and cause hallucinations, and presents a temporal segmented clustering method that outperforms baselines to enhance RAG performance on QA tasks.
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.