Query rewriting plays a vital role in enhancing conversational search by
transforming context-dependent user queries into standalone forms. Existing
approaches primarily leverage human-rewritten queries as labels to train query
rewriting models. However, human rewrites may lack sufficient information for
optimal retrieval performance. To overcome this limitation, we propose
utilizing large language models (LLMs) as query rewriters, enabling the
generation of informative query rewrites through well-designed instructions. We
define four essential properties for well-formed rewrites and incorporate all
of them into the instruction. In addition, we introduce the role of rewrite
editors for LLMs when initial query rewrites are available, forming a
``rewrite-then-edit'' process. Furthermore, we propose distilling the rewriting
capabilities of LLMs into smaller models to reduce rewriting latency. Our
experimental evaluation on the QReCC dataset demonstrates that informative
query rewrites can yield substantially improved retrieval performance compared
to human rewrites, especially with sparse retrievers.

通过利用大型语言模型作为查询重写器，并结合精心设计的指令，我们定义了四个重写的关键属性，提出了基于大型语言模型的查询重写方法。我们还介绍了 LLMs 的重写能力的提炼，并采用 “先重写后编辑” 的方法来处理初始查询重写。实验结果在 QReCC 数据集上表明，信息丰富的查询重写可以显著提高检索性能，特别是在检索器稀疏的情况下。