When completing knowledge-intensive tasks, humans sometimes need not just an
answer but also a corresponding reference passage for auxiliary reading.
Previous methods required obtaining pre-segmented article chunks through
additional retrieval models. This paper explores leveraging the parameterized
knowledge stored during the pre-training phase of large language models (LLMs)
to independently recall reference passage from any starting position. We
propose a two-stage framework that simulates the scenario of humans recalling
easily forgotten references. Initially, the LLM is prompted to recall document
title identifiers to obtain a coarse-grained document set. Then, based on the
acquired coarse-grained document set, it recalls fine-grained passage. In the
two-stage recall process, we use constrained decoding to ensure that content
outside of the stored documents is not generated. To increase speed, we only
recall a short prefix in the second stage, then locate its position to retrieve
a complete passage. Experiments on KILT knowledge-sensitive tasks have verified
that LLMs can independently recall reference passage location in various task
forms, and the obtained reference significantly assist downstream tasks.

本文研究了利用大型语言模型（LLMs）预训练阶段存储的参数化知识，独立地从任意起始位置检索参考段落的方法，并提出了一个模拟人类检索易被遗忘参考的两阶段框架。实验证明，LLMs 能够独立检索各种任务形式中的参考段落位置，并且获取的参考对下游任务产生了显著帮助。