QueryExplorer: An Interactive Query Generation Assistant for Search and Exploration

TL;DR

QueryExplorer is an interactive platform that combines large language models and retrieval systems to assist users in formulating, reformulating, and exploring search queries with human feedback, supporting research in complex search tasks.

Contribution

It introduces an interactive query generation and reformulation interface integrating LLMs with retrieval pipelines, enabling human-in-the-loop experiments and detailed user feedback logging.

Findings

Supports effective query creation and modification.

Enables detailed logging of user interactions and feedback.

Facilitates research on complex search and query formulation.

Abstract

Formulating effective search queries remains a challenging task, particularly when users lack expertise in a specific domain or are not proficient in the language of the content. Providing example documents of interest might be easier for a user. However, such query-by-example scenarios are prone to concept drift, and the retrieval effectiveness is highly sensitive to the query generation method, without a clear way to incorporate user feedback. To enable exploration and to support Human-In-The-Loop experiments we propose QueryExplorer -- an interactive query generation, reformulation, and retrieval interface with support for HuggingFace generation models and PyTerrier's retrieval pipelines and datasets, and extensive logging of human feedback. To allow users to create and modify effective queries, our demo supports complementary approaches of using LLMs interactively, assisting the user with edits and feedback at multiple stages of the query formulation process. With support for recording fine-grained interactions and user annotations, QueryExplorer can serve as a valuable experimental and research platform for annotation, qualitative evaluation, and conducting Human-in-the-Loop (HITL) experiments for complex search tasks where users struggle to formulate queries.