A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models

TL;DR

This paper introduces a setwise prompting method for zero-shot document ranking with large language models, achieving a better balance of effectiveness and efficiency compared to existing pointwise and pairwise approaches.

Contribution

The paper presents the first setwise prompting approach for LLM-based zero-shot ranking, demonstrating improved efficiency while maintaining high effectiveness through comprehensive evaluation.

Findings

Setwise approach reduces inference and token consumption.

Setwise approach maintains high ranking effectiveness.

Compared to existing methods, it offers better efficiency-effectiveness trade-offs.

Abstract

We propose a novel zero-shot document ranking approach based on Large Language Models (LLMs): the Setwise prompting approach. Our approach complements existing prompting approaches for LLM-based zero-shot ranking: Pointwise, Pairwise, and Listwise. Through the first-of-its-kind comparative evaluation within a consistent experimental framework and considering factors like model size, token consumption, latency, among others, we show that existing approaches are inherently characterised by trade-offs between effectiveness and efficiency. We find that while Pointwise approaches score high on efficiency, they suffer from poor effectiveness. Conversely, Pairwise approaches demonstrate superior effectiveness but incur high computational overhead. Our Setwise approach, instead, reduces the number of LLM inferences and the amount of prompt token consumption during the ranking procedure, compared to previous methods. This significantly improves the efficiency of LLM-based zero-shot ranking, while also retaining high zero-shot ranking effectiveness. We make our code and results publicly available at \url{https://github.com/ielab/llm-rankers}.