通过优化查询扩展的融合方式，显著提升稠密检索效果。
Query Expansion Is More Than Generation: Improving Dense Retrieval through Better Integration
- 分离编码原始查询与扩展文本，再动态插值融合
- 在多个数据集上提升检索效果最高达12.89%
- 无需训练，适合快速部署到现有检索系统
大型语言模型可生成查询扩展而无需任务特定训练，但相同扩展常使冻结的稠密检索器性能下降。我们发现一个被忽视的因素：以往研究多关注生成了什么文本，而对生成文本如何融入稠密检索器缺乏系统关注。在固定生成扩展的前提下，我们发现性能下降往往源于集成方法本身。为此提出AnchorQE，一种无训练方法：分别编码原始查询与扩展文本，再通过在线无监督策略估计插值系数，仅需少量未标注测试流即可完成。该策略仅在扩展文本既检索强又与原始查询检索证据一致时赋予高可信度。实验表明，相比广泛使用的仅扩展或文本拼接基线，AnchorQE在TREC-DL、LoTTE和BEIR数据集上检索效果最高提升12.89%。此外，其在线策略估计插值系数的效果优于在开发集上调好的固定权重，最高提升3.81%。
原文摘要 · Abstract (English)
Large language models (LLMs) can generate query expansions without task-specific training, yet the same expansions often make a frozen dense retriever worse. We identify an underexplored factor: prior work has often focused on what text is generated, while how generated text is incorporated into dense retrievers has received less systematic attention. By holding generated expansions fixed, we show that performance degradation can often be attributed to the integration method itself. We introduce AnchorQE, a training-free method that separately encodes the original query and its expansion before interpolating them. The interpolation factor is estimated using an unsupervised online strategy that operates over a small part of the unlabeled test stream. Intuitively, our strategy assigns high expansion trust only when expansions are both retrieval-strong and consistent with the original query's retrieved evidence. We show that AnchorQE improves retrieval effectiveness by up to 12.89% when compared to widely-used expansion-only or text-level concatenation baselines across TREC-DL, LoTTE, and BEIR. Further, we show that our online strategy to estimate the interpolation factor outperforms a fixed weight tuned on a development partition by up to 3.81%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。