众包分类体系验证：一种通过在线搜索交互优化知识图谱关系的反馈驱动框架

Introduction

简介

The efficacy of semantic search relies on the accuracy of the underlying Knowledge Graph (KG). In high-velocity domains like on-demand food delivery or e-commerce, the catalog of entities like dishes, products, and merchants changes rapidly.

语义搜索的有效性依赖于底层知识图谱（KG）的准确性。在按需外卖或电子商务等高速变化的领域，菜品、产品和商家等实体的目录变化迅速。

Current methods for KG construction and maintenance face three critical challenges:

当前用于KG构建和维护的方法面临三个关键挑战：

• Inaccuracy and hallucination from Large Language Models (LLMs): Automated models often infer relationships based on statistical text co-occurrence rather than semantic reality. For instance, an LLM might incorrectly classify “Pho” as a child of “Italian Noodle Soup” due to linguistic similarity, leading to irrelevant search results.
• 大型语言模型（LLMs）的不准确性与幻觉：自动化模型通常基于统计文本共现而非语义现实来推断关系。例如，由于语言相似性，LLM 可能会错误地将“Pho”归类为“意大利面汤”的子类，从而导致不相关的搜索结果。
• Scalability limits of manual verification: Traditional verification relies on human annotators or domain experts. This approach is slow, expensive, and unable to keep pace with dynamic catalogs containing millions of entities. For example, daily changes in restaurant menus or grocery stock keeping units (SKUs).
• 人工验证的可扩展性限制：传统验证依赖于人工标注员或领域专家。这种方法速度慢、成本高，且无法跟上包含数百万实体的动态目录的步伐。例如，餐厅菜单的日常更改或杂货库存量单位（SKU）的变化。
• Error propagation in ranking: Inaccurate graph edges propagate errors downstream. If a parent-child relationship is wrong, query expansion algorithms will retrieve irrelevant items, directly degrading Click-Through Rate (CTR) and user trust.
• 排序中的错误传播：不准确的图边会将错误向下游传播。如果父子关系错误，查询扩展算法将检索到不相关的项目，直接降低点击率（CTR）和用户信任度。

We introduce a feedback-driven verification engine that operationalizes the search interface as a validation environment. Key contributions include:

我们引入了一个反馈驱动的验证引擎，将搜索界面转化为验证环境。主要贡献包括：

• User feedback-driven verification: The system treats unverified graph edges as hypotheses. Instead of accepting them as truth, it tests them against live traffic by injecting them into search suggestions and measuring user engagement.
• 用户反馈驱动的验证：系统将未验证的图边视为假设。系统不直接将其视为事实，而是通...