Generative Query Reformulation Using Ensemble Prompting, Document Fusion, and Relevance Feedback

TL;DR

This paper introduces ensemble prompting and relevance feedback techniques for zero-shot query reformulation, significantly improving retrieval effectiveness and establishing new state-of-the-art results across multiple benchmarks.

Contribution

It proposes novel ensemble-based prompting methods and relevance feedback variants that enhance zero-shot query reformulation for information retrieval.

Findings

Up to 18% improvement in nDCG@10 in pre-retrieval settings

Up to 9% improvement in post-retrieval settings

Outperforms all previously reported state-of-the-art methods

Abstract

Query Reformulation (QR) is a set of techniques used to transform a user's original search query to a text that better aligns with the user's intent and improves their search experience. Recently, zero-shot QR has been a promising approach due to its ability to exploit knowledge inherent in large language models. Inspired by the success of ensemble prompting strategies which have benefited other tasks, we investigate if they can improve query reformulation. In this context, we propose two ensemble-based prompting techniques, GenQREnsemble and GenQRFusion which leverage paraphrases of a zero-shot instruction to generate multiple sets of keywords to improve retrieval performance ultimately. We further introduce their post-retrieval variants to incorporate relevance feedback from a variety of sources, including an oracle simulating a human user and a "critic" LLM. We demonstrate that an ensemble of query reformulations can improve retrieval effectiveness by up to 18% on nDCG@10 in pre-retrieval settings and 9% on post-retrieval settings on multiple benchmarks, outperforming all previously reported SOTA results. We perform subsequent analyses to investigate the effects of feedback documents, incorporate domain-specific instructions, filter reformulations, and generate fluent reformulations that might be more beneficial to human searchers. Together, the techniques and the results presented in this paper establish a new state of the art in automated query reformulation for retrieval and suggest promising directions for future research.