PreQRAG -- Classify and Rewrite for Enhanced RAG

TL;DR

PreQRAG is a novel RAG architecture that classifies questions and applies targeted rewriting to enhance retrieval and generation quality, demonstrated by competitive results in the LiveRAG challenge.

Contribution

It introduces a question classification and rewriting pipeline for RAG systems, improving retrieval and generation for both single- and multi-document questions.

Findings

Achieved second place in the LiveRAG challenge.

Improved retrieval precision and generation relevance.

Effective handling of complex multi-document questions.

Abstract

This paper presents the submission of the UDInfo team to the SIGIR 2025 LiveRAG Challenge. We introduce PreQRAG, a Retrieval Augmented Generation (RAG) architecture designed to improve retrieval and generation quality through targeted question preprocessing. PreQRAG incorporates a pipeline that first classifies each input question as either single-document or multi-document type. For single-document questions, we employ question rewriting techniques to improve retrieval precision and generation relevance. For multi-document questions, we decompose complex queries into focused sub-questions that can be processed more effectively by downstream components. This classification and rewriting strategy improves the RAG performance. Experimental evaluation of the LiveRAG Challenge dataset demonstrates the effectiveness of our question-type-aware architecture, with PreQRAG achieving the preliminary second place in Session 2 of the LiveRAG challenge.