This paper introduces PAG-a novel optimization and decoding approach that guides autoregressive generation of document identifiers in generative retrieval models through simultaneous decoding. To this aim, PAG constructs a set-based and sequential identifier for each document. Motivated by the bag-of-words assumption in information retrieval, the set-based identifier is built on lexical tokens. The sequential identifier, on the other hand, is obtained via quantizing relevance-based representations of documents. Extensive experiments on MSMARCO and TREC Deep Learning Track data reveal that PAG outperforms the state-of-the-art generative retrieval model by a large margin (e.g., 15.6% MRR improvements on MS MARCO), while achieving 22x speed up in terms of query latency.

翻译：本文提出了一种新颖的优化与解码方法PAG，通过同步解码引导生成式检索模型中文档标识符的自回归生成。为此，PAG为每篇文档构建了基于集合和基于序列两种标识符。受信息检索中词袋假设的启发，基于集合的标识符建立在词汇标记之上，而基于序列的标识符则通过对文档的关联性表示进行量化得到。在MSMARCO和TREC深度学习赛道数据上的大量实验表明，PAG在显著超越最先进生成式检索模型的同时（如MS MARCO上MRR提升15.6%），还将查询延迟降低22倍。