研究人员开发了RPTune，一个旨在提高大语言模型在目录搜索方面的性能的框架，特别针对中小型企业。该系统将学习型目录策展与大语言模型后训练相结合，使用自动生成的监督。RPTune的策展器根据大语言模型的反馈对产品进行排序和修剪，而后训练则使大语言模型能够更好地利用这些策展的上下文。在七个真实商户上的评估显示搜索准确性显著提高，仅上下文策展就将性能提高了31.4个百分点，后训练平均额外提高了10.3个百分点。 AI
影响 增强了大语言模型在电子商务搜索中的实用性，可能改善客户体验和大型目录企业的销售。
排序理由 该集群包含一篇详细介绍新框架及其评估的学术论文。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2610.00964v1 Announce Type: cross Abstract: For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-stage retrieval designed primarily for large marketplaces with millions of items. H…
For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-stage retrieval designed primarily for large marketplaces with millions of items. However, fitting the full catalog into the context …
For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-stage retrieval designed primarily for large marketplaces with millions of items. However, fitting the full catalog into the context …
For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-stage retrieval designed primarily for large marketplaces with millions of items. However, fitting the full catalog into the context …