Precise Zero-Shot Dense Retrieval without Relevance Labels
Luyu Gao † Xueguang Ma ‡ Jimmy Lin‡ Jamie Callan† †Language Technologies Institute, Carnegie Mellon University ‡David R. Cheriton School of Computer Science, University of Waterloo {luyug, {x93ma, Equal contribution.
Abstract
While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the difficulty of zero-shot learning and encoding relevance. Instead, we propose to pivot through Hypothetical Document Embeddings (HyDE). Given a query, HyDE first zero-shot instructs an instruction-following language model (e.g. InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is unreal and may contain false details. Then, an unsupervised contrastively learned encoder (e.g. Contriever) encodes the document into an embedding vector. This vector identifies a neighborhood in the corpus embedding space, where similar real documents are retrieved based on vector similarity. This second step ground the generated document to the actual corpus, with the encoder’s dense bottleneck filtering out the incorrect details. Our experiments show that HyDE significantly outperforms the state-of-the-art unsupervised dense retriever Contriever and shows strong performance comparable to fine-tuned retrievers, across various
中文速览
零样本稠密检索（zero-shot dense retrieval）在没有任何相关性标注数据的情况下效果很差，因为同时学习查询和文档的嵌入映射极其困难。为此，研究者提出了"假设文档嵌入"（Hypothetical Document Embeddings，HyDE）方法：先用指令跟随大语言模型（如 InstructGPT）根据用户查询"凭空"生成一篇假设性文档，再用无监督对比学习编码器（如 Contriever）将这篇文档编码成向量，最后用该向量在真实文档库中做相似度检索——语言模型负责捕捉相关性模式，编码器的信息瓶颈则自动过滤掉生成文档中的错误细节，从而把检索锚定在真实语料上。实验表明，HyDE 在网页搜索、问答、事实核查等多类任务以及斯瓦希里语、韩语、日语等多种语言上均大幅超越无监督基线 Contriever，甚至接近在大规模标注数据上微调过的检索模型。这项工作的意义在于，它完全无需训练或相关性标注，开箱即用，为低资源场景下的信息检索提供了一条切实可行的新路径。
原文 arXiv:2212.10496;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2212.10496v1