BriefGPT.xyz
Aug, 2023
基于大型语言模型的文档扩展预训练用于密集式段落检索
Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval
HTML
PDF
Guangyuan Ma, Xing Wu, Peng Wang, Zijia Lin, Songlin Hu
TL;DR
利用LLM（大型语言模型）进行文档扩展进行预训练，显著提升了大规模网络搜索任务中的检索性能。
Abstract
In this paper, we systematically study the potential of
pre-training
with Large Language Model(LLM)-based
document expansion
for dense
passage re
→