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：可验证生成旨在使大型语言模型（LLM）生成附带支持文档的文本，从而允许用户灵活验证答案，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：检索到的文档不仅能补充知识以帮助LLM生成正确答案，还可作为用户验证LLM输出的支持性证据。然而，广泛使用的检索器成为整个流程的瓶颈，限制了整体性能。由于检索器通常参数远少于大型语言模型，且尚未被证明能良好扩展至LLM规模，其能力往往弱于LLM。若检索器未能正确找到支持文档，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。为解决这些局限，我们提出LLatrieval（大型语言模型验证式检索），该方法使LLM持续更新检索结果，直至验证检索到的文档能充分支持回答问题。通过这种迭代机制，LLM可向检索过程提供反馈，促使检索结果完全支撑可验证生成。实验表明，LLatrieval显著超越多个基线方法，实现了最先进的性能。