QueryGenie: Making LLM-Based Database Querying Transparent and Controllable

TL;DR

QueryGenie is an interactive system that enhances transparency and control in LLM-based database querying by enabling users to monitor, understand, and guide query generation through real-time validation and iterative refinement.

Contribution

It introduces an interactive framework that allows users to oversee and influence LLM-driven database queries, addressing issues of misinterpretation and hallucination.

Findings

Improves query accuracy through real-time validation.

Enables iterative refinement for better user control.

Reduces misinterpretation and hallucination in query generation.

Abstract

Conversational user interfaces powered by large language models (LLMs) have significantly lowered the technical barriers to database querying. However, existing tools still encounter several challenges, such as misinterpretation of user intent, generation of hallucinated content, and the absence of effective mechanisms for human feedback-all of which undermine their reliability and practical utility. To address these issues and promote a more transparent and controllable querying experience, we proposed QueryGenie, an interactive system that enables users to monitor, understand, and guide the LLM-driven query generation process. Through incremental reasoning, real-time validation, and responsive interaction mechanisms, users can iteratively refine query logic and ensure alignment with their intent.