LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation
For practitioners needing entity linking across domains without retraining, LELA offers a practical zero-shot solution.
LELA is an LLM-based entity linking framework that provides a complete end-to-end pipeline with zero-shot domain adaptation, validated across diverse settings.
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.