DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG

TL;DR

This paper introduces DynamicER, a benchmark and method for resolving emerging mentions to dynamic entities in evolving knowledge bases, improving retrieval and generation in RAG systems by handling new expressions effectively.

Contribution

The paper presents a new task, benchmark, and a temporal clustering method for resolving emerging mentions, addressing limitations of existing entity linking models in dynamic contexts.

Findings

Our method outperforms baselines in entity linking accuracy.

Enhanced RAG performance on QA tasks with resolved mentions.

Effective management of temporal dynamics in evolving entities.

Abstract

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.