A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition

Excerpt

arXiv:2610.02970v2 Announce Type: replace Abstract: Large language models (LLMs) have shown promising potential for biomedical named entity recognition (BioNER) through instruction following and in-context learning. However, existing LLM-based BioNER methods still face two key limitations. First, retrieved demonstrations and external biomedical knowledge provide limited support for dataset-specific annotation semantics, leaving entity boundaries, type scopes, and annotation conventions ambiguous