面向Schema-as-Code生物医学命名实体识别的指南增强多智能体框架
A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition
浏览论文内容
中文总结 AI 辅助
针对现有LLM在BioNER中标注语义支持不足和结构控制缺失的问题，提出指南增强多智能体框架GAMA，通过规则归纳验证、规划编码及双循环细化，在五个数据集上稳定超越强基线。
中文摘要 AI 辅助
大型语言模型（LLMs）通过指令遵循和上下文学习，在生物医学命名实体识别（BioNER）方面显示出良好的潜力。然而，现有的基于LLM的BioNER方法仍面临两个关键限制。首先，检索到的演示和外部生物医学知识对数据集特定的标注语义支持有限，导致实体边界、类型范围和标注约定模糊不清。其次，自由形式的生成缺乏足够的结构控制，常常导致格式无效、幻觉提及、重复实体和边界错误。为解决这些限制，我们提出了GAMA，一个用于schema-as-code BioNER的指南增强多智能体框架。GAMA首先从带标签的训练实例中归纳候选标注规则，并对照标注数据验证这些规则，以构建可靠的数据集特定指南记忆。在这些经过验证的规则指导下，规划组件生成带有理由的排序跨度类型假设，编码组件将这些假设转换为受schema约束的实体对象。随后，验证模块检查跨度基础、类型有效性和结构合规性，并执行双循环细化以纠正无效或低置信度的预测。在五个广泛使用的BioNER数据集上使用多种LLM骨干进行的实验表明，GAMA始终优于强LLM基线。消融和参数分析进一步验证了所提出组件的有效性。
英文摘要
Large language models (LLMs) have shown promising potential for biomedical named entity recognition (BioNER) through instruction following and in-context learning. However, existing LLM-based BioNER methods still face two key limitations. First, retrieved demonstrations and external biomedical knowledge provide limited support for dataset-specific annotation semantics, leaving entity boundaries, type scopes, and annotation conventions ambiguous. Second, free-form generation lacks sufficient structural control, often leading to invalid formats, hallucinated mentions, duplicated entities, and boundary errors. To address these limitations, we propose GAMA, a guideline-augmented multi-agent framework for schema-as-code BioNER. GAMA first induces candidate annotation rules from labeled training instances and verifies them against annotated data to construct reliable dataset-specific guideline memory. Guided by these verified rules, a planning component generates ranked span-type hypotheses with rationales, and a coding component converts them into schema-constrained entity objects. A verification module then checks span grounding, type validity, and structural compliance, and performs dual-loop refinement to correct invalid or low-confidence predictions. Experiments on five widely used BioNER datasets with multiple LLM backbones show that GAMA consistently outperforms strong LLM-based baselines. Ablation and parameter analyses further verify the effectiveness of the proposed components.
发表机构
- Dalian Maritime University（大连海事大学）
- Beijing Institute of Technology（北京理工大学）
- Northeastern University（东北大学）
- Dalian University of Technology（大连理工大学）
机构由 AI 辅助整理，请以论文原文为准。
