基于大型语言模型的零样本列表式文档重排序（英文版）

英文标题：Zero-Shot Listwise Document Reranking with a Large Language Model中文摘要：在 TREC 网络搜索数据集和 MIRACL 跨语言数据集上，使用无需特定任务训练数据的 Listwise Reranker with a Large Language Model (LRL) 可以作为第一阶段和最终阶段的重新排序方法，在多层文本排序任务中取得了强大的效果。英文摘要：Supervised ranking methods based on bi-encoder or cross-encoder architectureshave shown success in multi-stage text ranking tasks, but they require largeamounts of relevance judgments as training data. In this work, we proposeListwise Reranker with a Large Language Model (LRL), whic