Large Language Models are Built-in Autoregressive Search Engines
This provides a novel, cost-effective solution for search engines by leveraging LLMs' in-context learning capabilities, though it is incremental as it builds on autoregressive search engines.
The paper tackles the problem of document retrieval for open-domain question answering by using large language models (LLMs) to generate URLs directly from queries, achieving nearly 90% accuracy in retrieving documents with correct answers and outperforming existing retrieval methods on benchmarks.
Document retrieval is a key stage of standard Web search engines. Existing dual-encoder dense retrievers obtain representations for questions and documents independently, allowing for only shallow interactions between them. To overcome this limitation, recent autoregressive search engines replace the dual-encoder architecture by directly generating identifiers for relevant documents in the candidate pool. However, the training cost of such autoregressive search engines rises sharply as the number of candidate documents increases. In this paper, we find that large language models (LLMs) can follow human instructions to directly generate URLs for document retrieval. Surprisingly, when providing a few {Query-URL} pairs as in-context demonstrations, LLMs can generate Web URLs where nearly 90\% of the corresponding documents contain correct answers to open-domain questions. In this way, LLMs can be thought of as built-in search engines, since they have not been explicitly trained to map questions to document identifiers. Experiments demonstrate that our method can consistently achieve better retrieval performance than existing retrieval approaches by a significant margin on three open-domain question answering benchmarks, under both zero and few-shot settings. The code for this work can be found at \url{https://github.com/Ziems/llm-url}.