In this paper, we present TWOLAR: a two-stage pipeline for passage reranking based on the distillation of knowledge from Large Language Models (LLM). TWOLAR introduces a new scoring strategy and a distillation process consisting in the creation of a novel and diverse training dataset. The dataset consists of 20K queries, each associated with a set of documents retrieved via four distinct retrieval methods to ensure diversity, and then reranked by exploiting the zero-shot reranking capabilities of an LLM. Our ablation studies demonstrate the contribution of each new component we introduced. Our experimental results show that TWOLAR significantly enhances the document reranking ability of the underlying model, matching and in some cases even outperforming state-of-the-art models with three orders of magnitude more parameters on the TREC-DL test sets and the zero-shot evaluation benchmark BEIR. To facilitate future work we release our data set, finetuned models, and code.

中文翻译：

---

TWOLAR：用于通道重排序的两步法学硕士增强蒸馏方法

在本文中，我们提出了 TWOLAR：基于大型语言模型 (LLM) 知识蒸馏的段落重新排序的两阶段管道。 TWOLAR 引入了一种新的评分策略和蒸馏过程，其中包括创建新颖且多样化的训练数据集。该数据集由 20K 个查询组成，每个查询与通过四种不同检索方法检索的一组文档相关联，以确保多样性，然后通过利用 LLM 的零样本重新排名功能进行重新排名。我们的消融研究证明了我们引入的每个新组件的贡献。我们的实验结果表明，TWOLAR 显着增强了基础模型的文档重新排序能力，匹配甚至在某些情况下超越了最先进的模型，在 TREC-DL 测试集和零-DL 测试集上参数增加了三个数量级。射击评估基准BEIR。为了方便未来的工作，我们发布了数据集、微调模型和代码。