用分块并行重排技术，快速处理超大候选集，性能超越传统方法。
JointRank: Rank Large Set with Single Pass
- 将候选集分块重排，利用局部排序推导隐式比较关系
- 在TREC DL-2019上实现nDCG@10达70.88，延迟从21秒降至8秒
- 适合大规模检索场景，无需修改现有模型架构
高效从大规模候选池中排序相关项是现代信息检索系统的核心——如网络搜索、推荐系统和检索增强生成。列表级重排模型虽能通过联合考虑多个候选项提升相关性，但常受限于模型输入长度或在处理大规模集合时性能下降。我们提出一种模型无关的快速重排方法，适用于超出模型输入限制的大规模候选集。该方法首先将候选项划分为重叠块，每块独立并行重排；随后从局部排序中推导隐式成对比较；最后利用胜率或PageRank等算法聚合全局排序。在TREC DL-2019上的实验表明，使用gpt-4.1-mini作为长上下文模型时，本方法nDCG@10达70.88，显著优于全上下文列表级方法的57.68，同时将延迟从21秒降至8秒。代码与实验已开源：https://github.com/V3RGANz/jointrank
原文摘要 · Abstract (English)
Efficiently ranking relevant items from large candidate pools is a cornerstone of modern information retrieval systems -- such as web search, recommendation, and retrieval-augmented generation. Listwise rerankers, which improve relevance by jointly considering multiple candidates, are often limited in practice: either by model input size constraints, or by degraded quality when processing large sets. We propose a model-agnostic method for fast reranking large sets that exceed a model input limits. The method first partitions candidate items into overlapping blocks, each of which is ranked independently in parallel. Implicit pairwise comparisons are then derived from these local rankings. Finally, these comparisons are aggregated to construct a global ranking using algorithms such as Winrate or PageRank. Experiments on TREC DL-2019 show that our method achieves an nDCG@10 of 70.88 compared to the 57.68 for full-context listwise approach using gpt-4.1-mini as long-context model, while reducing latency from 21 to 8 seconds. The implementation of the algorithm and the experiments is available in the repository: https://github.com/V3RGANz/jointrank
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。