查询扩展不止是生成：通过更好的集成改进密集检索
Query Expansion Is More Than Generation: Improving Dense Retrieval through Better Integration
浏览论文内容
中文总结 AI 辅助
该研究针对LLM生成查询扩展导致密集检索器性能下降的问题，提出无需训练的AnchorQE方法，通过编码原始查询与扩展内容并插值，在多个数据集上提升检索效果。
中文摘要 AI 辅助
大型语言模型（LLMs）无需针对特定任务训练即可生成查询扩展内容，但相同的扩展内容往往会使冻结的密集检索器性能变差。我们发现一个未被充分研究的因素：现有研究通常关注生成的文本内容，而对如何将生成的文本集成到密集检索器中的系统关注较少。在保持生成的扩展内容固定的情况下，我们表明性能下降通常可归因于集成方法本身。我们提出AnchorQE，这是一种无需训练的方法，它对原始查询及其扩展内容分别进行编码后再进行插值，插值因子通过一种在未标记测试流的小部分上运行的无监督在线策略进行估计。直观地说，我们的策略仅在扩展内容既具备检索能力又与原始查询的检索证据一致时，才会赋予其高可信度。我们在TREC-DL、LoTTE和BEIR数据集上的实验表明，与广泛使用的仅扩展或文本级拼接基线相比，AnchorQE可将检索效果提升多达12.89%；此外，我们还表明，用于估计插值因子的在线策略比在开发分区上调优的固定权重性能提升多达3.81%。
英文摘要
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%.
