用测试时计算提升检索效果，让小模型变聪明且可解释。
Rank1: Test-Time Compute for Reranking in Information Retrieval
- 利用大模型推理过程训练小模型，实现测试时快速增强性能。
- 在60万条MS MARCO数据上训练，显著提升复杂任务与指令遵循能力。
- 模型可解释、低资源，适合需要透明性和高效性的搜索系统。
我们提出Rank1，首个利用测试时计算进行重排序的模型。Rank1通过蒸馏大型推理语言模型（如OpenAI的o1、Deepseek的R1）的推理轨迹，在不增加推理延迟的前提下显著提升小型模型的性能。我们收集并开源了超过60万条来自MS MARCO的R1推理轨迹数据。基于该数据训练的模型在先进推理和指令遵循数据集上达到当前最优表现；由于能响应用户输入提示，具有出色的分布外泛化能力；同时具备可解释的推理链，可供用户或RAG系统使用。此外，量化后的模型仍保持强性能，同时降低计算与内存开销。总体而言，Rank1证明了测试时计算能够构建一种新型、可解释且高性能的检索重排序模型。
原文摘要 · Abstract (English)
We introduce Rank1, the first reranking model trained to take advantage of test-time compute. Rank1 demonstrates the applicability within retrieval of using a reasoning language model (i.e. OpenAI's o1, Deepseek's R1, etc.) for distillation in order to rapidly improve the performance of a smaller model. We gather and open-source a dataset of more than 600,000 examples of R1 reasoning traces from queries and passages in MS MARCO. Models trained on this dataset show: (1) state-of-the-art performance on advanced reasoning and instruction following datasets; (2) work remarkably well out of distribution due to the ability to respond to user-input prompts; and (3) have explainable reasoning chains that can be given to users or RAG-based systems. Further, we demonstrate that quantized versions of these models retain strong performance while using less compute/memory. Overall, Rank1 shows that test-time compute allows for a fundamentally new type of explainable and performant reranker model for search.
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。