跨模型相似度对齐新方法，提升检索系统迁移性
Mapping Similarity Spaces across Embedding Models with Synthetic Query Probing
- 用合成查询生成技术构建可控数据对，无需参考即可分析模型间相似度行为
- 不同模型绝对相似度存在系统性偏差，线性与保序回归可部分对齐分布
- 适合需要迁移或统一阈值的检索增强系统开发者使用
检索增强生成系统依赖相似度得分来召回相关内容，但因嵌入模型几何特性差异，得分无法直接跨模型比较，阻碍了模型迁移并限制阈值复用。本文通过学习得分分布间的映射关系，而非嵌入向量本身，来建立相似度关联。提出合成查询探测（Synthetic Query Probing）方法，从文档生成查询，构建受控的查询-片段对，实现大规模、无参考的跨模型相似度行为分析。在SciFact和一个专有语料库上评估多种嵌入配置，采用线性、保序及分位数映射学习得分转换函数。实验表明，尽管模型排序基本一致，其绝对得分存在系统性扭曲。学习到的映射可部分对齐相似度空间，提升阈值可移植性，其中保序回归表现最佳。结果强调跨模型校准的重要性，并将合成查询探测定位为可扩展的嵌入可比性分析框架。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation systems rely on similarity scores to retrieve relevant content, yet scores are not directly comparable across embedding models due to differing geometric properties, complicating model migration and limiting threshold reuse. We study how similarity scores can be related by learning mappings between score distributions rather than embeddings. We introduce Synthetic Query Probing, generating queries from documents to create controlled query-chunk pairs, enabling large-scale, reference-free analysis of cross-model similarity behavior. We evaluate the approach on multiple embedding configurations and learn score conversion functions using linear, isotonic, and quantile mappings. Experiments on SciFact and a proprietary corpus show that while models largely agree on rankings, their absolute scores exhibit systematic distortions. Learned mappings partially align these spaces and improve threshold portability, with isotonic regression performing best. Our results highlight the need for cross-model calibration and position Synthetic Query Probing as a scalable framework for analyzing embedding comparability.
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。