Recent progress in information retrieval finds that embedding query and
document representation into multi-vector yields a robust bi-encoder retriever
on out-of-distribution datasets. In this paper, we explore whether late
interaction, the simplest form of multi-vector, is also helpful to neural
rerankers that only use the [CLS] vector to compute the similarity score.
Although intuitively, the attention mechanism of rerankers at the previous
layers already gathers the token-level information, we find adding late
interaction still brings an extra 5% improvement in average on
out-of-distribution datasets, with little increase in latency and no
degradation in in-domain effectiveness. Through extensive experiments and
analysis, we show that the finding is consistent across different model sizes
and first-stage retrievers of diverse natures and that the improvement is more
prominent on longer queries.

本文探讨了将后期交互用于神经重排器的有用性，以提高其在分布外数据集中的性能，该方法能带来额外的 5％改进，而无需增加太多的延迟和没有影响其在域内数据上的效果，通过实验和分析，发现这一结论与模型大小和不同类型的第一阶段检索器一致，并且这种改进在较长的查询上更为显著。

通过上下文化的后期交互提高神经重排器的超领域泛化能力

Improving Out-of-Distribution Generalization of Neural Rerankers with Contextualized Late Interaction

Pre-trained language models are increasingly important components across
multiple information retrieval (IR) paradigms. Late interaction, introduced
with the ColBERT model and recently refined in ColBERTv2, is a popular paradigm
that holds state-of-the-art status across many benchmarks. To dramatically
speed up the search latency of late interaction, we introduce the
Performance-optimized Late Interaction Driver (PLAID). Without impacting
quality, PLAID swiftly eliminates low-scoring passages using a novel centroid
interaction mechanism that treats every passage as a lightweight bag of
centroids. PLAID uses centroid interaction as well as centroid pruning, a
mechanism for sparsifying the bag of centroids, within a highly-optimized
engine to reduce late interaction search latency by up to 7$\times$ on a GPU
and 45$\times$ on a CPU against vanilla ColBERTv2, while continuing to deliver
state-of-the-art retrieval quality. This allows the PLAID engine with ColBERTv2
to achieve latency of tens of milliseconds on a GPU and tens or just few
hundreds of milliseconds on a CPU at large scale, even at the largest scales we
evaluate with 140M passages.

本研究通过引入性能优化的虚拟中心点交互机制，构建一个名为 PLAID 的优化 late interaction 模型引擎，极大地加速 late interaction 搜索延迟，同时保持准确度。通过在 GPU 和 CPU 上的测试表明，该引擎在大规模情况下甚至可以实现毫秒级的搜索延迟。