轻量微调让模型自适应多向量压缩，高压缩比下仍保持检索精度。
Learn to Pool: Lightweight Fine-Tuning for Flexible Multi-Vector Compression
- 用k-means微调实现轻量级池化感知训练
- 在BEIR SciFact上实现83%向量压缩且准确率不降
- 单模型适配多种压缩率，适合实际部署
后期交互模型表现出强泛化能力，常优于更大规模的密集嵌入模型。其广泛部署的挑战在于每文档产生大量词元向量，带来存储与内存开销。推理时对词元进行池化可显著降低向量数量，且对检索精度影响有限。大规模池化感知训练在高压缩率下表现更优。本文提出轻量微调作为实用替代方案，发现即使仅用k-means进行最小程度的池化感知训练，也能大幅优于仅推理时池化的方法；并展现出跨池化方法与数据集的迁移能力；通过多因素训练，可得到一个在不同压缩率下均有效的单一模型。最强模型在BEIR SciFact上，于池化因子1-6下均超越未池化基线，意味着在83%向量压缩率下仍无精度损失。
原文摘要 · Abstract (English)
Late interaction models have shown strong generalization capabilities, often outperforming much larger dense embedding models. One challenge to their widespread deployment is the large number of token vectors they produce per document and the associated storage and memory costs. Pooling tokens at inference time has shown great promise to reduce the vector count with limited effects on retrieval accuracy. Large-scale pooling-aware training has demonstrated even more impressive results at high compression rates. We propose lightweight fine-tuning as a practical alternative and find that even minimal pooling-aware training with k-means yields broad gains over inference-only pooling, shows evidence of transfer across pooling methods and datasets, and - with multi-factor training - produces a single model effective across different compression levels. Our strongest model outperforms the unpooled baseline on BEIR SciFact across pool factors 1-6, implying a vector compression rate of 83% at no cost to retrieval accuracy.
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。