arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.17152cs.IRcs.CL
收藏

利用大型语言模型提升 Pinterest 搜索相关性

Improving Pinterest Search Relevance Using Large Language Models

Pinterest

Han Wang, Mukuntha Narayanan Sundararaman, Onur Gungor, Yu Xu, Krishna Kamath, Rakesh Chalasani, Kurchi Subhra Hazra, Jinfeng Rao

AI总结:

本文提出将大型语言模型集成到 Pinterest 搜索相关性模型中,通过多模态文本表示、半监督学习和多语言扩展提升训练数据规模,并将模型蒸馏为可实时服务的架构,最终在大规模部署中验证了相关性提升效果。

摘要:

为了改进 Pinterest 搜索的相关性评分,我们将大型语言模型(LLMs)集成到搜索相关性模型中,利用精心设计的文本表示来有效预测 Pin 的相关性。我们的方法将搜索查询与内容表示结合使用,这些内容表示包括从生成式视觉语言模型中提取的说明文字。这些表示进一步通过基于链接的文本数据、历史上高质量的互动查询、用户策展的画板、Pin 标题和 Pin 描述进行丰富,从而构建出用于预测搜索相关性的稳健模型。我们采用半监督学习方法高效地扩大训练数据规模,超越现有昂贵的人工标注数据。通过利用多语言 LLMs,我们的系统将训练数据扩展到未见过的语言和领域,尽管初始数据和标注者专业知识仅限于英语。此外,我们将基于 LLM 的模型蒸馏为可实时服务的模型架构和特征。我们为所提出的技术提供了全面的离线实验验证,并展示了最终部署系统在大规模场景下所取得的收益。

英文摘要:

To improve relevance scoring on Pinterest Search, we integrate Large Language Models (LLMs) into our search relevance model, leveraging carefully designed text representations to predict the relevance of Pins effectively. Our approach uses search queries alongside content representations that include captions extracted from a generative visual language model. These are further enriched with link-based text data, historically high-quality engaged queries, user-curated boards, Pin titles and Pin descriptions, creating robust models for predicting search relevance. We use a semi-supervised learning approach to efficiently scale up the amount of training data, expanding beyond the expensive human labeled data available. By utilizing multilingual LLMs, our system extends training data to include unseen languages and domains, despite initial data and annotator expertise being confined to English. Furthermore, we distill from the LLM-based model into real-time servable model architectures and features. We provide comprehensive offline experimental validation for our proposed techniques and demonstrate the gains achieved through the final deployed system at scale.

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。

↑