Unified Active Retrieval for Retrieval Augmented Generation

TL;DR

This paper introduces Unified Active Retrieval (UAR), a novel approach that uses four criteria for better retrieval timing decisions in Retrieval-Augmented Generation, improving performance and reducing complexity.

Contribution

The paper proposes a unified, plug-and-play framework with four criteria for active retrieval, simplifying the process and enhancing effectiveness across diverse instruction types.

Findings

UAR outperforms existing methods in retrieval timing accuracy

UAR improves downstream task performance

UAR reduces inference latency

Abstract

In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Therefore, determining whether to retrieve is crucial for RAG, which is usually referred to as Active Retrieval. However, existing active retrieval methods face two challenges: 1. They usually rely on a single criterion, which struggles with handling various types of instructions. 2. They depend on specialized and highly differentiated procedures, and thus combining them makes the RAG system more complicated and leads to higher response latency. To address these challenges, we propose Unified Active Retrieval (UAR). UAR contains four orthogonal criteria and casts them into plug-and-play classification tasks, which achieves multifaceted retrieval timing judgements with negligible extra inference cost. We further introduce the Unified Active Retrieval Criteria (UAR-Criteria), designed to process diverse active retrieval scenarios through a standardized procedure. Experiments on four representative types of user instructions show that UAR significantly outperforms existing work on the retrieval timing judgement and the performance of downstream tasks, which shows the effectiveness of UAR and its helpfulness to downstream tasks.