arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.11136cs.IRcs.CLcs.LG
收藏

Promptriever:经过指令训练的检索器可以像语言模型一样被提示

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

Johns Hopkins University(约翰斯·霍普金斯大学);Samaya AI(萨马亚人工智能公司)

Orion Weller, Benjamin Van Durme, Dawn Lawrie, Ashwin Paranjape, Yuhao Zhang, Jack Hessel

AI总结:

本研究提出首个可像语言模型一样被提示的检索模型Promptriever,基于MS MARCO构建近50万实例的指令训练集,在相关性指令遵循、查询鲁棒性、提示式超参搜索上均取得显著提升,为检索模型的提示控制研究奠定基础。

摘要:

经过指令微调的语言模型(LM)能够响应祈使命令,与其基础版本相比提供了更自然的用户界面。在本研究中,我们提出了Promptriever——首个能够像LM一样被提示的检索模型。为训练Promptriever,我们基于MS MARCO整理并发布了一个新的实例级指令训练集,涵盖近50万个实例。Promptriever不仅在标准检索任务上表现优异,还能遵循指令。我们观察到:(1)在遵循详细相关性指令方面取得大幅提升(达到当前最优水平),在FollowIR上p-MRR提升14.3、nDCG提升3.1;(2)对查询+指令中的词汇选择/措辞的鲁棒性显著增强,在InstructIR上Robustness@10提升12.9;(3)具备通过提示进行超参数搜索以可靠提升检索性能的能力,在BEIR上平均提升1.4。Promptriever证明检索模型可基于每个查询通过提示进行控制,为未来将LM提示技术与信息检索对齐的研究奠定了基础。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑