跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2511.14718 · v4

Natural Language Interfaces for Databases: What Changes for SQL-Literate Users?

首次提交 2025-11-19 02:04
版本更新 2026-11-07 11:29
雷达观测 2026-11-10 11:14
arXiv ↗PDF ↗

摘要

Natural Language Interfaces for Databases (NLIDBs) let users query data in everyday language instead of SQL, and modern systems translate most questions accurately. Does an NLIDB remove the work of querying, or move it? We compared SQL-LLM, a GPT-4o-backed NLIDB, with Snowflake, a manual-SQL platform. Twenty SQL-literate professionals and graduate students, ten per interface, each completed 12 BIRD benchmark tasks with hints naming target columns and operators. SQL-LLM cut completion time per query by 31%. It did not improve accuracy: SQL-LLM users answered 46% of queries correctly versus 64% for Snowflake, a gap this sample cannot confirm (p=0.08p = 0.08) that narrows to 14 points without one session where the system timed out. Think-aloud audio from 11 participants (4 SQL-LLM, 7 Snowflake) showed how the work shifted: SQL-LLM users left initial schema navigation to the model, mainly on easier tasks, and focused on checking the generated SQL, while Snowflake users explored the schema and wrote queries by hand. Coded behavior rates did not differ detectably between arms, and positive remarks during a task did not reliably predict a correct answer. The evidence fits a reallocation of querying work, not its removal: users still had to check the generated SQL.

作者备注:29 pages, 4 figures, 5 tables

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v4,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v4 · 2026-11-07 11:29 · 最新观测版本

Natural Language Interfaces for Databases: What Changes for SQL-Literate Users?

Natural Language Interfaces for Databases (NLIDBs) let users query data in everyday language instead of SQL, and modern systems translate most questions accurately. Does an NLIDB remove the work of querying, or move it? We compared SQL-LLM, a GPT-4o-backed NLIDB, with Snowflake, a manual-SQL platform. Twenty SQL-literate professionals and graduate students, ten per interface, each completed 12 BIRD benchmark tasks with hints naming target columns and operators. SQL-LLM cut completion time per query by 31%. It did not improve accuracy: SQL-LLM users answered 46% of queries correctly versus 64% for Snowflake, a gap this sample cannot confirm (p=0.08p = 0.08) that narrows to 14 points without one session where the system timed out. Think-aloud audio from 11 participants (4 SQL-LLM, 7 Snowflake) showed how the work shifted: SQL-LLM users left initial schema navigation to the model, mainly on easier tasks, and focused on checking the generated SQL, while Snowflake users explored the schema and wrote queries by hand. Coded behavior rates did not differ detectably between arms, and positive remarks during a task did not reliably predict a correct answer. The evidence fits a reallocation of querying work, not its removal: users still had to check the generated SQL.

查看此版本解读 →查看此版本原文 ↗