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

翻译：本文提出InstUPR，一种基于大语言模型的无监督段落重排序方法。与现有依赖查询-文档对或检索特定指令进行大量训练的方法不同，我们的方法利用指令微调后的大语言模型遵循指令的能力进行段落重排序，无需额外微调。为实现这一目标，我们引入软分数聚合技术，并采用成对重排序来实现无监督段落重排序。在BEIR基准上的实验表明，InstUPR在性能上优于无监督基线方法和指令微调的重排序器，验证了其有效性和优越性。所有实验的复现源代码已在https://github.com/MiuLab/InstUPR开源。