AI RESEARCH
SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition
arXiv CS.AI
•
ArXi:2605.03706v1 Announce Type: cross Zero-shot Named Entity Recognition (ZS-NER) remains brittle under domain and schema shifts, where unseen label definitions often misalign with a large language model's (LLM's) intrinsic semantic organization. As a result, directly mapping entity mentions to fine-grained target labels can induce systematic semantic drift, especially when target schemas are novel or semantically overlapping.