嵌入手术：稠密检索中自适应排序修正的局部更新方法
Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval
浏览论文内容
中文总结 AI 辅助
本研究提出嵌入手术方法，通过对选定文档嵌入的局部最小化更新实现稠密检索的自适应排序修正，在多个基准上取得显著性能提升，且与查询适配方法互补。
中文摘要 AI 辅助
稠密检索系统是现代搜索引擎、推荐平台及检索增强生成（RAG）流程的核心组件，它将文档与查询编码为稠密嵌入，可通过向量相似度实现高效语义搜索。但由于文档嵌入是离线计算并存储在静态索引中，这类系统难以适应用户反馈或不断变化的搜索意图。为解决这一局限，我们提出嵌入手术（embedding surgery），一种用于稠密检索中自适应排序修正的轻量级方法。该方法在查询时根据编辑反馈、用户交互或大语言模型的伪标签，对选定的文档嵌入施加局部、最小化的更新。我们将嵌入手术建模为凸优化问题，该问题在对受影响文档表示的修改最小化的同时强制执行排序约束。我们将嵌入手术集成到标准稠密检索流程中，并在TREC Deep Learning、TREC Robust、TREC CAsT和MS MARCO基准上进行评估。结果显示，即使在有噪声或变化的反馈下，其仍能实现持续改进（例如，在编辑反馈下，DL-Hard任务的nDCG@10相对提升高达60.64%），且计算成本低，不会破坏嵌入空间的全局结构。大量实验表明，排序修正会传播到语义相关的查询，嵌入更新可通过简单的原地覆盖安全高效地应用于可扩展的近似最近邻（ANN）索引，无需代价高昂的索引重建。最后，嵌入手术与CoRocchio等查询适配方法互补，在更抗噪声反馈的同时可获得额外收益。
英文摘要
Dense retrieval systems are core components of modern search engines, recommendation platforms, and retrieval-augmented generation pipelines. They encode documents and queries into dense embeddings, enabling efficient semantic search via vector similarity. However, because document embeddings are computed offline and stored in static indexes, these systems struggle to adapt to user feedback or evolving search intent. To address this limitation, we introduce \emph{embedding surgery}, a lightweight approach for adaptive ranking correction in dense retrieval. The method applies localized, minimal updates to selected document embeddings at query time, guided by editorial feedback, user interactions, or pseudo-labels from large language models. We formulate embedding surgery as a convex optimization problem that enforces ranking constraints while minimizing modifications to the affected document representations. We integrate embedding surgery into standard dense retrieval pipelines and evaluate it on TREC Deep Learning, TREC Robust, TREC CAsT, and MS MARCO benchmarks. Results show consistent improvements (e.g., up to +60.64\% relative improvement in nDCG@10 on DL-Hard under editorial feedback), even under noisy or shifting feedback, with low computational cost and without disrupting the global structure of the embedding space. Extensive experiments show that ranking corrections propagate to semantically related queries and that embedding updates can be applied safely and efficiently to scalable Approximate Nearest Neighbor indexes via simple in-place overwriting, without requiring costly index reconstruction. Finally, embedding surgery complements query adaptation methods such as CoRocchio, yielding additional gains while being more robust to noisy feedback.
发表机构
- IIT-CNR（意大利国家研究委员会信息科学与技术研究所）
- Seltz
- ISTI-CNR（意大利国家研究委员会信息科学与技术研究所）
机构由 AI 辅助整理，请以论文原文为准。
