GenCRF: Generative Clustering and Reformulation Framework for Enhanced Intent-Driven Information Retrieval

TL;DR

GenCRF introduces a novel framework that uses generative clustering and reformulation with LLMs to capture diverse user intents, significantly improving retrieval effectiveness in IR tasks.

Contribution

The paper presents the first adaptive query reformulation framework that clusters generated queries to represent diverse intents and integrates a feedback mechanism for enhanced IR performance.

Findings

Achieves up to 12% improvement in nDCG@10 on BEIR benchmark.

Effectively captures diverse user intents through clustering of generated queries.

Enhances retrieval performance by combining multiple intent representations.

Abstract

Query reformulation is a well-known problem in Information Retrieval (IR) aimed at enhancing single search successful completion rate by automatically modifying user's input query. Recent methods leverage Large Language Models (LLMs) to improve query reformulation, but often generate limited and redundant expansions, potentially constraining their effectiveness in capturing diverse intents. In this paper, we propose GenCRF: a Generative Clustering and Reformulation Framework to capture diverse intentions adaptively based on multiple differentiated, well-generated queries in the retrieval phase for the first time. GenCRF leverages LLMs to generate variable queries from the initial query using customized prompts, then clusters them into groups to distinctly represent diverse intents. Furthermore, the framework explores to combine diverse intents query with innovative weighted aggregation strategies to optimize retrieval performance and crucially integrates a novel Query Evaluation Rewarding Model (QERM) to refine the process through feedback loops. Empirical experiments on the BEIR benchmark demonstrate that GenCRF achieves state-of-the-art performance, surpassing previous query reformulation SOTAs by up to 12% on nDCG@10. These techniques can be adapted to various LLMs, significantly boosting retriever performance and advancing the field of Information Retrieval.