Conversational search provides a natural interface for information retrieval (IR). Recent approaches have demonstrated promising results in applying dense retrieval to conversational IR. However, training dense retrievers requires large amounts of in-domain paired data. This hinders the development of conversational dense retrievers, as abundant in-domain conversations are expensive to collect. In this paper, we propose CONVERSER, a framework for training conversational dense retrievers with at most 6 examples of in-domain dialogues. Specifically, we utilize the in-context learning capability of large language models to generate conversational queries given a passage in the retrieval corpus. Experimental results on conversational retrieval benchmarks OR-QuAC and TREC CAsT 19 show that the proposed CONVERSER achieves comparable performance to fully-supervised models, demonstrating the effectiveness of our proposed framework in few-shot conversational dense retrieval. All source code and generated datasets are available at https://github.com/MiuLab/CONVERSER

翻译：会话搜索为信息检索提供了自然交互界面。近期方法在将密集检索应用于会话式信息检索方面展现出良好前景。然而，训练密集检索器需要大量领域内配对数据，这阻碍了会话密集检索器的发展，因为收集充足的领域内会话成本高昂。本文提出CONVERSER框架，该框架仅需最多6条领域内对话示例即可训练会话密集检索器。具体而言，我们利用大型语言模型的情境学习能力，根据检索语料库中的段落生成会话查询。在会话检索基准测试OR-QuAC和TREC CAsT 19上的实验结果表明，所提出的CONVERSER在性能上与全监督模型相当，验证了该框架在少样本会话密集检索中的有效性。所有源代码和生成数据集均可在https://github.com/MiuLab/CONVERSER获取。