基于大模型的实体链接框架，支持零样本领域自适应。
LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation
- 构建端到端大模型实体链接系统，集成零样本命名实体识别。
- 在多种场景下表现稳健，跨领域适应性强。
- 提供可交互的Python库，适合实际应用开发。
实体链接是众多下游NLP系统的关键组件，但现有方法通常依赖特定知识库和领域，限制了实际应用。本文将LELA——一种模块化、领域无关的大模型实体消歧方法——扩展为实用的Python库，集成零样本命名实体识别（NER），从而构建完整的端到端实体链接流水线，适用于真实场景。实验验证了LELA在多样化实体链接设置中的性能与鲁棒性。演示中，用户可对自有文本进行交互式测试。
原文摘要 · Abstract (English)
Entity linking is a key component of many downstream NLP systems, yet existing approaches are often tied to the specific target knowledge bases and domains, limiting their real world application. In this paper, we extend LELA, a modular and domain-agnostic LLM-based entity disambiguation method, into a practical Python library that integrates zero-shot Named Entity Recognition (NER) -thereby providing a complete end-toend pipeline for entity-linking in real-world usage. We provide experimental results validating LELA's performance and robustness across diverse entity linking settings. In our demo, users can play with the system on their own input texts.
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。