{"ID":2830876,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.10043","arxiv_id":"2512.10043","title":"Local LLM Ensembles for Zero-shot Portuguese Named Entity Recognition","abstract":"Large Language Models (LLMs) excel in many Natural Language Processing (NLP) tasks through in-context learning but often under-perform in Named Entity Recognition (NER), especially for lower-resource languages like Portuguese. While open-weight LLMs enable local deployment, no single model dominates all tasks, motivating ensemble approaches. However, existing LLM ensembles focus on text generation or classification, leaving NER under-explored. In this context, this work proposes a novel three-step ensemble pipeline for zero-shot NER using similarly capable, locally run LLMs. Our method outperforms individual LLMs in four out of five Portuguese NER datasets by leveraging a heuristic to select optimal model combinations with minimal annotated data. Moreover, we show that ensembles obtained on different source datasets generally outperform individual LLMs in cross-dataset configurations, potentially eliminating the need for annotated data for the current task. Our work advances scalable, low-resource, and zero-shot NER by effectively combining multiple small LLMs without fine-tuning. Code is available at https://github.com/Joao-Luz/local-llm-ner-ensemble.","short_abstract":"Large Language Models (LLMs) excel in many Natural Language Processing (NLP) tasks through in-context learning but often under-perform in Named Entity Recognition (NER), especially for lower-resource languages like Portuguese. While open-weight LLMs enable local deployment, no single model dominates all tasks, motivati...","url_abs":"https://arxiv.org/abs/2512.10043","url_pdf":"https://arxiv.org/pdf/2512.10043v1","authors":"[\"João Lucas Luz Lima Sarcinelli\",\"Diego Furtado Silva\"]","published":"2025-12-10T19:55:06Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":606082,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2830876,"paper_url":"https://arxiv.org/abs/2512.10043","paper_title":"Local LLM Ensembles for Zero-shot Portuguese Named Entity Recognition","repo_url":"https://github.com/Joao-Luz/local-llm-ner-ensemble","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}