EL4NER ensembles three small open-source LLMs with task decomposition, span-aware retrieval, and self-verification, reporting competitive or better NER F1 than GPT-4o-based baselines on two of three datasets.
[CLS]entity1[ SEP]type1[CLS]entity2[SEP]type2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EL4NER: Ensemble Learning for Named Entity Recognition via Multiple Small-Parameter Large Language Models
EL4NER ensembles three small open-source LLMs with task decomposition, span-aware retrieval, and self-verification, reporting competitive or better NER F1 than GPT-4o-based baselines on two of three datasets.