Boosting Portuguese NER: Local LLM Ensembles Excel at Zero-Shot Performance

The study explores the effectiveness of local Large Language Model (LLM) ensembles for Named Entity Recognition (NER) in Portuguese, demonstrating strong zero-shot performance. This research contributes valuable insights into leveraging local LLMs for specific language tasks without extensive training data.

• •Leverages local LLM ensembles for Portuguese NER.
• •Achieves strong performance in a zero-shot setting.
• •Offers a practical approach for language-specific tasks.