用少量标签提升查询理解，无需重索引文档
Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval
- 先对齐强查询与轻量文档嵌入空间，再用小样本标签微调
- 在126个任务中，异构场景下nDCG@10提升超12点
- 适合标签稀缺但需增强查询理解的检索系统
密集检索系统面临指令类查询复杂、文档集静态简化的不对称问题。尽管更强的查询嵌入模型能更好理解查询，但重新嵌入大规模语料或微调大模型常不现实。我们提出高效检索适配器（ERA），一种无需重索引的查询侧适配学习框架。ERA首先利用无标签语料文档对齐强查询嵌入器与轻量文档嵌入器的嵌入空间，再以少量标注的查询-文档对适应对齐后的查询表示。在来自六个领域的126个MAIR检索任务中，ERA在对称设置下平均nDCG@10提升最多8.2点，在非对称设置下提升超过12点，且所需标签数远少于监督式适配训练。结果表明，检索系统可在不更新主干嵌入器或重建文档索引的前提下，受益于更强的查询理解能力。
原文摘要 · Abstract (English)
Dense retrieval systems increasingly face an asymmetry between complex instruction-like queries and relatively simple, static document collections. While stronger embedders can better understand such queries, re-embedding large corpora or fine-tuning large models is often impractical. We propose Efficient Retrieval Adapter (ERA), a query-side adapter learning framework for re-index-free retrieval adaptation. ERA first aligns the embedding spaces of a strong query embedder and a lightweight document embedder using unlabeled corpus documents, and then adapts the aligned query representation with a small number of labeled query-document pairs. Across 126 MAIR retrieval tasks from six domains, ERA improves average nDCG@10 by up to 8.2 points in symmetric settings and by more than 12 points in asymmetric settings, while using substantially fewer labels than supervised adapter training. These results show that retrieval systems can benefit from stronger query understanding without updating backbone embedders or rebuilding document indexes.
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。