ISEE: Interactive Semantic Enrichment for Database Fields
On the map: LLM agents and tool use → Web, search, and research agents
Abstract (arXiv)
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. 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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 19 of its 36 references that are in the map. First posted on arXiv 21 Apr 2026.
Builds on
19 of 36 references.
References · 19
- 2024A Survey on LLM-as-a-Judgecited by 1,384
- 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
- 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
- 2019Asking Clarifying Questions in Open-Domain Information-Seeking Conversationscited by 136
- 2018End-to-End Neural Entity Linkingcited by 85
- 2019Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Studycited by 40
- 2023Interactive Text-to-SQL Generation via Editable Step-by-Step Explanationscited by 19
- 2024Selective Prompt Anchoring for Code Generationcited by 16
- 2024Insights into Natural Language Database Query Errors: From Attention Misalignment to User Handling Strategiescited by 11
- 2024SQLucid: Grounding Natural Language Database Queries with Interactive Explanationscited by 10
- 2024Synthetic SQL Column Descriptions and Their Impact on Text-to-SQL Performancecited by 6
7 more
- 2025Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotationcited by 6
- 2025Automatic database description generation for Text-to-SQLcited by 5
- 2025Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Modelscited by 5
- 2026EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolutioncited by 5
- 2026PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agentscited by 5
- 2025Supporting Construction Worker Well-Being with a Multi-Agent Conversational AI Systemcited by 3
- 2024LLM as a Scorer: The Impact of Output Order on Dialogue Evaluationcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025RAISE: Reasoning Agent for Interactive SQL Exploration
- 2025TEXT2DB: Integration-Aware Information Extraction with Large Language Model Agents
- 2025DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning
- 2025LLM and Agent-Driven Data Analysis: A Systematic Approach for Enterprise Applications and System-level Deployment
- 2025FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data
- 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
- 2022Beyond Interestingness: Semantic and Context-Aware Natural Language Query Recommendations for Visual Data Analysis
- 2025AskDB: An LLM Agent for Natural Language Interaction with Relational Databases