用关键词检索提升通用嵌入模型在私有数据上的表现
Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval
- 用BM25检索结果生成监督信号，指导嵌入模型适配私有数据
- 在多个领域和数据集上均实现检索性能提升
- 适合需要将通用模型用于行业专有数据的场景
文本嵌入模型在AI应用中起核心作用，如检索增强生成（RAG）。尽管通用文本嵌入模型在通用检索基准上表现良好，但在包含专业术语的私有数据（如企业专属数据）上效果下降。本文提出BMEmbed，一种将通用文本嵌入模型适配至私有数据的新方法。通过利用成熟的关键词检索技术（BM25），构建基于检索排序的监督信号，以促进模型适应。我们在多个领域、数据集和模型上评估BMEmbed，均显示检索性能持续提升。此外，我们实证分析了BM25信号如何通过增强对齐性和均匀性来改善嵌入质量，凸显该方法在领域特定数据适配中的价值。源代码已开源：https://github.com/BaileyWei/BMEmbed。
原文摘要 · Abstract (English)
Text embedding models play a cornerstone role in AI applications, such as retrieval-augmented generation (RAG). While general-purpose text embedding models demonstrate strong performance on generic retrieval benchmarks, their effectiveness diminishes when applied to private datasets (e.g., company-specific proprietary data), which often contain specialized terminology and lingo. In this work, we introduce BMEmbed, a novel method for adapting general-purpose text embedding models to private datasets. By leveraging the well-established keyword-based retrieval technique (BM25), we construct supervisory signals from the ranking of keyword-based retrieval results to facilitate model adaptation. We evaluate BMEmbed across a range of domains, datasets, and models, showing consistent improvements in retrieval performance. Moreover, we provide empirical insights into how BM25-based signals contribute to improving embeddings by fostering alignment and uniformity, highlighting the value of this approach in adapting models to domain-specific data. We release the source code available at https://github.com/BaileyWei/BMEmbed for the research community.
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。