Recent work in zero-shot listwise reranking using LLMs has achieved state-of-the-art results. However, these methods are not without drawbacks. The proposed methods rely on large LLMs with billions of parameters and limited context sizes. This paper introduces LiT5-Distill and LiT5-Score, two methods for efficient zero-shot listwise reranking, leveraging T5 sequence-to-sequence encoder-decoder models. Our approaches demonstrate competitive reranking effectiveness compared to recent state-of-the-art LLM rerankers with substantially smaller models. Through LiT5-Score, we also explore the use of cross-attention to calculate relevance scores to perform reranking, eliminating the reliance on external passage relevance labels for training. We present a range of models from 220M parameters to 3B parameters, all with strong reranking results, challenging the necessity of large-scale models for effective zero-shot reranking and opening avenues for more efficient listwise reranking solutions. We provide code and scripts to reproduce our results at https://github.com/castorini/LiT5.

翻译：近期利用大语言模型（LLM）进行零样本列表式重排序的研究取得了最先进的结果。然而，这些方法并非没有缺点。所提出的方法依赖于具有数十亿参数和有限上下文规模的庞大LLM。本文介绍了LiT5-Distill和LiT5-Score两种方法，用于高效零样本列表式重排序，利用了T5序列到序列编码器-解码器模型。我们的方法在重排序效果上与近期最先进的基于LLM的重排序器相比具有竞争力，且模型规模显著缩小。通过LiT5-Score，我们还探索了利用交叉注意力计算相关性分数以执行重排序，从而消除了训练时对外部段落相关性标签的依赖。我们提供了一系列参数规模从2.2亿到30亿的模型，均表现出强大的重排序结果，挑战了大规模模型在高效零样本重排序中的必要性，并为更高效的列表式重排序解决方案开辟了途径。我们在https://github.com/castorini/LiT5上提供了代码和脚本以复现我们的结果。