让检索模型像语言模型一样用提示词控制，提升指令遵循与鲁棒性。
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
- 通过指令训练构建可提示的检索模型，支持自然语言指令输入。
- 在FollowIR上提升14.3 p-MRR，InstructIR鲁棒性提升12.9@10。
- 支持通过提示词自动调参，显著提升检索性能，适合交互式检索场景。
指令微调的语言模型能响应命令式指令，相比基础版本提供更自然的用户界面。本文提出首个可如语言模型般被提示的检索模型——Promptriever。为训练该模型，我们从MS MARCO构建并发布了一个包含近50万实例的层级指令训练集。Promptriever不仅在标准检索任务中表现优异，还能准确遵循指令。实验发现：(1) 在详细相关性指令任务FollowIR上取得显著提升（p-MRR+14.3，nDCG+3.1），达到当前最佳水平；(2) 对查询与指令中的词汇选择/表达方式具有更强鲁棒性（InstructIR Robustness@10提升12.9）；(3) 可通过提示词进行超参数搜索，稳定提升检索性能（BEIR平均提升1.4）。结果表明，检索模型可通过提示词实现按查询定制化控制，为未来将语言模型提示技术与信息检索对齐奠定基础。
原文摘要 · Abstract (English)
Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts. In this work, we present Promptriever, the first retrieval model able to be prompted like an LM. To train Promptriever, we curate and release a new instance-level instruction training set from MS MARCO, spanning nearly 500k instances. Promptriever not only achieves strong performance on standard retrieval tasks, but also follows instructions. We observe: (1) large gains (reaching SoTA) on following detailed relevance instructions (+14.3 p-MRR / +3.1 nDCG on FollowIR), (2) significantly increased robustness to lexical choices/phrasing in the query+instruction (+12.9 Robustness@10 on InstructIR), and (3) the ability to perform hyperparameter search via prompting to reliably improve retrieval performance (+1.4 average increase on BEIR). Promptriever demonstrates that retrieval models can be controlled with prompts on a per-query basis, setting the stage for future work aligning LM prompting techniques with information 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。