Rank-K通过测试时推理提升多语言列表重排序效果
Rank-K: Test-Time Reasoning for Listwise Reranking
- 利用大模型推理能力在查询时动态重排文档列表
- 相比RankZephyr，BM25初始结果重排提升23%，SPLADE-v3提升19%
- 支持多语言查询，跨语言重排效果不降
检索-重排是常见检索流程，可使计算量大的重排模型在查询时更高效。近年神经重排模型借助大语言模型的推理能力，在查询与段落间进行深度关联分析，达到顶尖检索效果。然而这类模型仍资源消耗大，即使经过优化也难以应对高负载。本文提出Rank-K，一种基于大语言模型推理能力的列表重排序模型，可在查询时实现测试时可扩展性，以应对复杂查询。实验表明，当对BM25初始排序列表重排时，Rank-K比当前最优的Listwise重排器RankZephyr提升23%；在使用SPLADE-v3生成的强检索结果上，仍能提升19%。由于Rank-K本身为多语言模型，其在不同语言查询下的段落排序效果与单语言场景相当。
原文摘要 · Abstract (English)
Retrieve-and-rerank is a popular retrieval pipeline because of its ability to make slow but effective rerankers efficient enough at query time by reducing the number of comparisons. Recent works in neural rerankers take advantage of large language models for their capability in reasoning between queries and passages and have achieved state-of-the-art retrieval effectiveness. However, such rerankers are resource-intensive, even after heavy optimization. In this work, we introduce Rank-K, a listwise passage reranking model that leverages the reasoning capability of the reasoning language model at query time that provides test time scalability to serve hard queries. We show that Rank-K improves retrieval effectiveness by 23\% over the RankZephyr, the state-of-the-art listwise reranker, when reranking a BM25 initial ranked list and 19\% when reranking strong retrieval results by SPLADE-v3. Since Rank-K is inherently a multilingual model, we found that it ranks passages based on queries in different languages as effectively as it does in monolingual retrieval.
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。