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
@article{arxiv.2403.16435,
title = {InstUPR : Instruction-based Unsupervised Passage Reranking with Large Language Models},
author = {Chao-Wei Huang and Yun-Nung Chen},
journal= {arXiv preprint arXiv:2403.16435},
year = {2024}
}
Comments
Preprint. This manuscript was originally written and submitted in June 2023