InstUPR : Instruction-based Unsupervised Passage Reranking with Large Language Models

TL;DR

Different from existing approaches that rely on extensive training with query-document pairs or retrieval-specific instructions, InstUPR leverages the instruction-following capabilities of instruction-tuned LLMs for passage reranking without any additional fine-tuning.

Abstract

This paper introduces InstUPR, an unsupervised passage reranking method based on large language models (LLMs). Different from existing approaches that rely on extensive training with query-document pairs or retrieval-specific instructions, our method leverages the instruction-following capabilities of instruction-tuned LLMs for passage reranking without any additional fine-tuning. To achieve this, we introduce a soft score aggregation technique and employ pairwise reranking for unsupervised passage reranking. Experiments on the BEIR benchmark demonstrate that InstUPR outperforms unsupervised baselines as well as an instruction-tuned reranker, highlighting its effectiveness and superiority. Source code to reproduce all experiments is open-sourced at https://github.com/MiuLab/InstUPR

Figures (2)

• Figure 1: Illustration of our proposed InstUPR framework, which includes pointwise reranking and pairwise reranking modules for fine-grained estimation.
• Figure 2: The instruction templates for reranking in InstUPR.