A Distributed Collaborative Retrieval Framework Excelling in All Queries and Corpora based on Zero-shot Rank-Oriented Automatic Evaluation

TL;DR

This paper introduces a Distributed Collaborative Retrieval Framework (DCRF) that unifies multiple retrieval models, dynamically selects the best results per query, and employs prompting strategies with large language models to evaluate ranking quality without labeled data, achieving superior performance and efficiency.

Contribution

The paper presents a novel DCRF that integrates diverse retrieval models and uses LLM-based prompting strategies for automatic evaluation, enhancing performance across all queries and corpora.

Findings

DCRF outperforms individual models across datasets.

The framework achieves comparable results to state-of-the-art listwise methods.

Prompting strategies enable effective rank evaluation without labeled data.

Abstract

Numerous retrieval models, including sparse, dense and llm-based methods, have demonstrated remarkable performance in predicting the relevance between queries and corpora. However, the preliminary effectiveness analysis experiments indicate that these models fail to achieve satisfactory performance on the majority of queries and corpora, revealing their effectiveness restricted to specific scenarios. Thus, to tackle this problem, we propose a novel Distributed Collaborative Retrieval Framework (DCRF), outperforming each single model across all queries and corpora. Specifically, the framework integrates various retrieval models into a unified system and dynamically selects the optimal results for each user's query. It can easily aggregate any retrieval model and expand to any application scenarios, illustrating its flexibility and scalability.Moreover, to reduce maintenance and training costs, we design four effective prompting strategies with large language models (LLMs) to evaluate the quality of ranks without reliance of labeled data. Extensive experiments demonstrate that proposed framework, combined with 8 efficient retrieval models, can achieve performance comparable to effective listwise methods like RankGPT and ListT5, while offering superior efficiency. Besides, DCRF surpasses all selected retrieval models on the most datasets, indicating the effectiveness of our prompting strategies on rank-oriented automatic evaluation.