用进化算法自动生成标注代码，低成本实现高精度专业领域训练数据。
EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision
- 三类智能代理迭代生成可执行标注代码，通过验证集反馈优化。
- 在8个专业任务中平均提升0.141宏F1，最快比LLM标注快3.1万倍。
- 适合标注成本高、需高精度的医学、法律等专业场景使用。
大语言模型在通用任务表现优异，但在标注成本高的专业高风险领域，其性能不如小型监督模型。本文提出EvoPool，一种受达尔文进化论启发的多智能体演化框架。三个专业化智能体迭代生成可执行的标注器代码，小规模验证集提供适应度信号，确定性门控机制筛选通过生存力、多样性及边际贡献检验的标注器。池化投票由EvoAgg聚合器映射为软标签，该聚合器结合语义特征与标注器投票特征。所生成的标注池每样本成本近乎为零，在10万样本上比LLM标注快4500至31000倍。在8个中7个涉及生物医学关系抽取、法律条款分类、复杂推理和密集多标签生物医学分类的弱监督专业任务中，EvoPool平均优于最强的LLM标注基线0.141宏F1，最高达0.301（ChemProt）和0.265（PubMed）。代码开源：https://github.com/tianyi0216/EvoPool。
原文摘要 · Abstract (English)
Large language models excel at general tasks but underperform smaller supervised models in specialized, high-stakes domains where training labels are costly. We address this regime with EvoPool, an evolutionary multi-agent framework inspired by Darwinian evolution. Three specialized agents iteratively propose executable annotator code, a small validation set provides a fitness signal, and a deterministic gate keeps only annotators that pass viability, diversity, and marginal-contribution checks across generations. Pool votes are mapped to soft training labels by EvoAgg, a text-aware aggregator combining semantic features with annotator-vote features. The authored pool runs at near-zero per-example cost and is 4500 to 31000x faster than LLM annotation on 100K examples. Across 7 of 8 LLM-weak specialized and complex tasks spanning biomedical relation extraction, legal-clause classification, complex reasoning, and dense multi-label biomedical classification, EvoPool beats the strongest LLM annotation baseline by an average +0.141 macro-F1, peaking at +0.301 on ChemProt and +0.265 on PubMed. Code is available at: https://github.com/tianyi0216/EvoPool
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。