Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting
This work addresses the challenge of enhancing conversational search for users by improving query rewriting, though it is incremental as it builds on existing LLM and distillation methods.
The paper tackles the problem of suboptimal retrieval performance in conversational search due to insufficient information in human-rewritten queries by using large language models (LLMs) to generate informative query rewrites, resulting in substantially improved retrieval performance, especially with sparse retrievers on the QReCC dataset.
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.