ISEE: Interactive Semantic Enrichment for Database Fields

ISEE：数据库字段的交互式语义增强

Abstract: LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval. However, their performance heavily depends on the clarity and completeness of data semantics. In practice, many field descriptions remain ambiguous or incomplete, as much of the essential context (e.g., the meaning of a customized field) originates from users’ domain knowledge and is rarely documented publicly. This gap restricts the agents’ task performance in downstream tasks, such as entity-linking.

摘要： 基于大语言模型（LLM）的智能体正越来越多地被部署用于数据相关任务，包括数据理解、探索和检索。然而，它们的性能在很大程度上取决于数据语义的清晰度和完整性。在实践中，许多字段描述往往含糊不清或不完整，因为许多关键背景信息（例如自定义字段的含义）源于用户的领域知识，且很少有公开文档记录。这种差距限制了智能体在实体链接等下游任务中的表现。

To bridge this gap, we introduce a novel and comprehensive Interactive SEmantic Enrichment system (ISEE). Given a data field description, ISEE measures its quality through a scoring system, gathers domain knowledge, and collaboratively enriches the semantics with users. Through a user study, automated user simulation, quantitative evaluation, and case study, we demonstrate that ISEE significantly reduces cognitive load, improves description quality, and enhances downstream task performance.

为了弥补这一差距，我们引入了一种新颖且全面的交互式语义增强系统（ISEE）。给定一个数据字段描述，ISEE 通过评分系统衡量其质量，收集领域知识，并与用户协作丰富语义。通过用户研究、自动化用户模拟、定量评估和案例研究，我们证明 ISEE 能够显著降低认知负荷、提高描述质量，并增强下游任务的性能。

---

Paper Details:

• Authors: Yuan Tian, Yiru Chen, Rakesh R. Menon, Zifan Liu, Ting Cai, Fei Wu, Anudeep Chimakurthi, Prashanthi Ramamurthy, Sridevi Aishwariya Ganesan, Kun Qian, Yunyao Li
• Submitted: 21 Apr 2026
• Subjects: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
• DOI: 10.48550/arXiv.2608.02604

论文详情：

• 作者： Yuan Tian, Yiru Chen, Rakesh R. Menon, Zifan Liu, Ting Cai, Fei Wu, Anudeep Chimakurthi, Prashanthi Ramamurthy, Sridevi Aishwariya Ganesan, Kun Qian, Yunyao Li
• 提交日期： 2026年4月21日
• 学科分类： 人工智能 (cs.AI)；信息检索 (cs.IR)
• DOI： 10.48550/arXiv.2608.02604