Synergistic Interplay between Search and Large Language Models for Information Retrieval

TL;DR

This paper introduces InteR, a framework that synergistically combines search engines and large language models to improve information retrieval accuracy through iterative refinement, outperforming existing methods on large-scale benchmarks.

Contribution

The paper presents a novel framework, InteR, that leverages the complementary strengths of RMs and LLMs for enhanced zero-shot information retrieval.

Findings

InteR achieves superior zero-shot retrieval performance.

The framework improves accuracy on web search and low-resource tasks.

Iterative refinement enhances both query understanding and document relevance.

Abstract

Information retrieval (IR) plays a crucial role in locating relevant resources from vast amounts of data, and its applications have evolved from traditional knowledge bases to modern retrieval models (RMs). The emergence of large language models (LLMs) has further revolutionized the IR field by enabling users to interact with search systems in natural languages. In this paper, we explore the advantages and disadvantages of LLMs and RMs, highlighting their respective strengths in understanding user-issued queries and retrieving up-to-date information. To leverage the benefits of both paradigms while circumventing their limitations, we propose InteR, a novel framework that facilitates information refinement through synergy between RMs and LLMs. InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections and enables LLMs to enhance prompt formulation using retrieved documents. This iterative refinement process augments the inputs of RMs and LLMs, leading to more accurate retrieval. Experiments on large-scale retrieval benchmarks involving web search and low-resource retrieval tasks demonstrate that InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods, even those using relevance judgment. Source code is available at https://github.com/Cyril-JZ/InteR