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

Abstract

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 ($p=0.08$) 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.

arXiv comment29 pages, 4 figures, 5 tables