LLM as Entity Disambiguator for Biomedical Entity-Linking

Entity linking involves normalizing a mention in medical text to a unique identifier in a knowledge base, such as UMLS or MeSH.Most entity linkers follow a two-stage process: first, a candidate generation step selects highquality candidates, and then a named entity disambiguation phase determines the best candidate for final linking.This study demonstrates that leveraging a large language model (LLM) as an entity disambiguator significantly enhances entity linking models' accuracy and recall.Specifically, the LLM disambiguator achieves remarkable improvements when applied to alias-matching entity linking methods.Without any fine-tuning, our approach establishes a new state-of-the-art (SOTA), surpassing previous methods on multiple prevalent biomedical datasets by up to 16 points in accuracy.