给检索模型的关键词加权，让重要词影响更大，提升搜索准确率。
Incorporating Token Importance in Multi-Vector Retrieval
- 用词重要性权重替代原版的固定距离计算，动态调整每个词的贡献
- 在BEIR基准上零样本提升1.28%，少量微调后达3.66%的召回率改善
- 无需改动文档向量，仅训练词权重，兼容现有系统且部署简单
ColBERT采用晚交互机制，独立编码查询与文档，通过细粒度的词级向量交互计算相似度。该设计既保持表达力又支持高效评分，因多向量文档表示可离线预计算。其使用类似Chamfer的距离函数：对每个查询词，选择最接近的文档词并求和。本文探索改进该距离函数，改用加权和方式计算查询词贡献，权重反映词的重要性。实验表明，仅需训练词权重而保持多向量表示不变，这一简单扩展显著提升了晚交互多向量机制的表达能力。尤其在BEIR基准上，使用基于IDF的权重实现零样本下Recall@10提升1.28%，通过少量微调进一步提升至3.66%。
原文摘要 · Abstract (English)
ColBERT introduced a late interaction mechanism that independently encodes queries and documents using BERT, and computes similarity via fine-grained interactions over token-level vector representations. This design enables expressive matching while allowing efficient computation of scores, as the multi-vector document representations could be pre-computed offline. ColBERT models distance using a Chamfer-style function: for each query token, it selects the closest document token and sums these distances across all query tokens. In our work, we explore enhancements to the Chamfer distance function by computing a weighted sum over query token contributions, where weights reflect the token importance. Empirically, we show that this simple extension, requiring only token-weight training while keeping the multi-vector representations fixed, further enhances the expressiveness of late interaction multi-vector mechanism. In particular, on the BEIR benchmark, our method achieves an average improvement of 1.28\% in Recall@10 in the zero-shot setting using IDF-based weights, and 3.66\% through few-shot fine-tuning.
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。