Verifiable generation aims to let the large language model (LLM) generate text with supporting documents, which enables the user to flexibly verify the answer and makes the LLM's output more reliable. Retrieval plays a crucial role in verifiable generation. Specifically, the retrieved documents not only supplement knowledge to help the LLM generate correct answers, but also serve as supporting evidence for the user to verify the LLM's output. However, the widely used retrievers become the bottleneck of the entire pipeline and limit the overall performance. Their capabilities are usually inferior to LLMs since they often have much fewer parameters than the large language model and have not been demonstrated to scale well to the size of LLMs. If the retriever does not correctly find the supporting documents, the LLM can not generate the correct and verifiable answer, which overshadows the LLM's remarkable abilities. To address these limitations, we propose \LLatrieval (Large Language Model Verified Retrieval), where the LLM updates the retrieval result until it verifies that the retrieved documents can sufficiently support answering the question. Thus, the LLM can iteratively provide feedback to retrieval and facilitate the retrieval result to fully support verifiable generation. Experiments show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results.

翻译：可验证生成旨在让大语言模型（LLM）生成附带支撑文档的文本，从而使用户能够灵活验证答案，并提升LLM输出的可靠性。检索在可验证生成中扮演关键角色：一方面，检索到的文档补充知识以帮助LLM生成正确答案；另一方面，这些文档作为用户验证LLM输出的支撑证据。然而，广泛使用的检索器成为整个流水线的瓶颈，限制了整体性能。由于检索器的参数量通常远小于LLM，且尚未证明其能随LLM规模有效扩展，其能力往往劣于LLM。若检索器未能正确找到支撑文档，LLM便无法生成正确且可验证的答案，这掩盖了LLM的卓越能力。为解决这一局限性，我们提出LLatrieval（大语言模型验证的检索方法），该方法让LLM不断更新检索结果，直至其验证检索到的文档能充分支撑问题回答。由此，LLM可迭代地向检索提供反馈，促进检索结果完全支持可验证生成。实验表明，LLatrieval显著优于多项基线方法，并取得了最先进的结果。