开源医学命名实体识别模型，12个数据集上10项刷新纪录。
OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets
- 用轻量领域适配预训练+低秩微调，仅更新1.5%参数
- 12个生物医学数据集上10项达新最优，基因类提升超9.7个百分点
- 单卡训练<12小时，碳排放低于1.2公斤，符合欧盟AI监管
命名实体识别（NER）是提取超过80%未结构化医疗数据中结构化信息的基础。尽管大语言模型取得进展，但在多样实体类型上实现先进性能并保持计算高效仍是挑战。本文提出OpenMed NER，一套开源、领域适配的Transformer模型，结合轻量级领域自适应预训练（DAPT）与参数高效的低秩微调（LoRA）。在包含35万段落的伦理合规公开语料库（来自PubMed、arXiv、MIMIC-III）上，使用DeBERTa-v3、PubMedBERT和BioELECTRA作为主干进行成本可控的DAPT，随后通过LoRA进行任务微调，仅更新少于1.5%的模型参数。我们在涵盖化学物、疾病、基因和物种的12个标准生物医学NER基准上评估模型。OpenMed NER在12个数据集中的10个上达到新的最佳微平均F1得分，在多种实体类型上均有显著提升。在基础疾病和化学物基准（如BC5CDR-Disease）上提升2.70个百分点，而在更专业的基因和临床细胞系数据集上提升超过5.3和9.7个百分点。该工作表明，经策略性适配的开源模型可超越封闭源代码方案。性能达成的同时极具效率：单卡训练时间不足12小时，碳足迹低于1.2公斤二氧化碳当量，产出的许可宽松的开源检查点有助于实践者满足欧盟《人工智能法案》等新兴数据保护与AI监管要求。
原文摘要 · Abstract (English)
Named-entity recognition (NER) is fundamental to extracting structured information from the >80% of healthcare data that resides in unstructured clinical notes and biomedical literature. Despite recent advances with large language models, achieving state-of-the-art performance across diverse entity types while maintaining computational efficiency remains a significant challenge. We introduce OpenMed NER, a suite of open-source, domain-adapted transformer models that combine lightweight domain-adaptive pre-training (DAPT) with parameter-efficient Low-Rank Adaptation (LoRA). Our approach performs cost-effective DAPT on a 350k-passage corpus compiled from ethically sourced, publicly available research repositories and de-identified clinical notes (PubMed, arXiv, and MIMIC-III) using DeBERTa-v3, PubMedBERT, and BioELECTRA backbones. This is followed by task-specific fine-tuning with LoRA, which updates less than 1.5% of model parameters. We evaluate our models on 12 established biomedical NER benchmarks spanning chemicals, diseases, genes, and species. OpenMed NER achieves new state-of-the-art micro-F1 scores on 10 of these 12 datasets, with substantial gains across diverse entity types. Our models advance the state-of-the-art on foundational disease and chemical benchmarks (e.g., BC5CDR-Disease, +2.70 pp), while delivering even larger improvements of over 5.3 and 9.7 percentage points on more specialized gene and clinical cell line corpora. This work demonstrates that strategically adapted open-source models can surpass closed-source solutions. This performance is achieved with remarkable efficiency: training completes in under 12 hours on a single GPU with a low carbon footprint (< 1.2 kg CO2e), producing permissively licensed, open-source checkpoints designed to help practitioners facilitate compliance with emerging data protection and AI regulations, such as the EU AI Act.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。