CoRE：面向结构化知识检索的协同自适应规则路由与约束
原标题：Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval
AI 摘要
该论文提出 CoRE 框架，用于结构化知识检索，无需预定义的查询-规则对监督。CoRE 通过强化学习训练路由智能体为每个查询分配推理规则，并通过对比学习训练规则约束检索器，二者交替优化、协同适应。在 STaRK-QA 数据集（科学发现、生物医学推理、电商企业知识管理）上验证了其优越性，消融实验表明路由与检索器协同适应有效，生成式路由具备跨数据集迁移能力。
正文节选
Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval Abstract Structured knowledge retrieval aims to acquire task-relevant evidence from structured knowledge sources for downstream task execution. Existing methods either rely on unconstrained retrieval or predefined query-rule supervision (e.g., author–paper for seeking papers in scientific discovery and anatomy–drug for precision medicine in biomedical analysis), which is rarely available in practice. To address this lim