低成本多语言检索系统，用英文查中文/波斯语/俄文新闻
WSDM Cup 2026 Multilingual Retrieval: A Low-Cost Multi-Stage Retrieval Pipeline
- 四阶段流水线：查询扩展+BM25候选+长文本嵌入排序+小顶堆重排
- nDCG@20达0.403，前20名相关率95%，在低算力下表现优异
- 适合资源有限但需跨语言检索的场景，可复用于多语种信息获取
我们提出一种针对WSDM Cup 2026多语言检索任务的低成本检索系统，使用英文查询从约一千万篇中文、波斯语和俄文新闻文章中检索相关文档，并为每个查询输出前1000名结果。系统采用四阶段流程：基于LLM的GRF风格查询扩展、BM25候选检索、使用jina-embeddings-v4生成的长文本表示进行密集排序，以及利用Qwen3-Reranker-4B对前20个候选进行点式重排，同时保留其余结果的密集排序顺序。在官方评测中，系统在nDCG@20上达到0.403，Judged@20为0.95。我们还进行了广泛的消融实验，量化各阶段贡献，并分析在有限算力下查询扩展、密集排序和前k重排的有效性。
原文摘要 · Abstract (English)
We present a low-cost retrieval system for the WSDM Cup 2026 multilingual retrieval task, where English queries are used to retrieve relevant documents from a collection of approximately ten million news articles in Chinese, Persian, and Russian, and to output the top-1000 ranked results for each query. We follow a four-stage pipeline that combines LLM-based GRF-style query expansion with BM25 candidate retrieval, dense ranking using long-text representations from jina-embeddings-v4, and pointwise re-ranking of the top-20 candidates using Qwen3-Reranker-4B while preserving the dense order for the remaining results. On the official evaluation, the system achieves nDCG@20 of 0.403 and Judged@20 of 0.95. We further conduct extensive ablation experiments to quantify the contribution of each stage and to analyze the effectiveness of query expansion, dense ranking, and top-$k$ reranking under limited compute budgets.
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。