In this work, we propose a simple method that applies a large language model (LLM) to large-scale retrieval in zero-shot scenarios. Our method, Language language model as Retriever (LameR) is built upon no other neural models but an LLM, while breaking up brute-force combinations of retrievers with LLMs and lifting the performance of zero-shot retrieval to be very competitive on benchmark datasets. Essentially, we propose to augment a query with its potential answers by prompting LLMs with a composition of the query and the query's in-domain candidates. The candidates, regardless of correct or wrong, are obtained by a vanilla retrieval procedure on the target collection. Such candidates, as a part of prompts, are likely to help LLM generate more precise answers by pattern imitation or candidate summarization. Even if all the candidates are wrong, the prompts at least make LLM aware of in-collection patterns and genres. Moreover, due to the low performance of a self-supervised retriever, the LLM-based query augmentation becomes less effective as the retriever bottlenecks the whole pipeline. So, we propose to leverage a non-parametric lexicon-based method (e.g., BM25) as the retrieval module to capture query-document overlap in a literal fashion. As such, LameR makes the retrieval procedure transparent to the LLM, so it circumvents the performance bottleneck.

翻译：本文提出了一种简单方法，将大型语言模型（LLM）应用于零样本场景下的大规模检索。我们的方法“语言模型作为检索器”（LameR）完全基于LLM构建，无需其他神经模型，同时打破了检索器与LLM的暴力组合，使零样本检索在基准数据集上达到极具竞争力的性能。本质上，我们通过将查询及其域内候选集组合成提示（prompt）输入LLM，来扩增查询的潜在答案。这些候选集（无论正确与否）是通过对目标集合进行基础检索流程获得的。此类候选集作为提示的一部分，可通过模式模仿或候选总结帮助LLM生成更精确的答案。即使所有候选结果均错误，提示至少能让LLM了解集合内的模式与体裁。此外，由于自监督检索器的性能较低，基于LLM的查询扩增效果会因检索器成为整个流程的瓶颈而减弱。为此，我们提出采用非参数化词法方法（例如BM25）作为检索模块，以字面方式捕捉查询与文档的重叠。通过这种方式，LameR使检索过程对LLM透明化，从而规避了性能瓶颈。