Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination. A promising solution to this issue is verifiable text generation, which prompts LLMs to generate content with citations for accuracy verification. However, verifiable text generation is non-trivial due to the focus-shifting phenomenon, the intricate reasoning needed to align the claim with correct citations, and the dilemma between the precision and breadth of retrieved documents. In this paper, we present VTG, an innovative framework for Verifiable Text Generation with evolving memory and self-reflection. VTG introduces evolving long short-term memory to retain both valuable documents and recent documents. A two-tier verifier equipped with an evidence finder is proposed to rethink and reflect on the relationship between the claim and citations. Furthermore, active retrieval and diverse query generation are utilized to enhance both the precision and breadth of the retrieved documents. We conduct extensive experiments on five datasets across three knowledge-intensive tasks and the results reveal that VTG significantly outperforms baselines.

翻译：尽管大型语言模型（LLM）在语言理解和生成方面展现出卓越能力，但其常会产生事实性错误信息，即所谓的“幻觉”问题。针对此问题，可验证文本生成是一种颇具前景的解决方案，其通过引导LLM生成附带引用的内容以实现准确性验证。然而，可验证文本生成面临多重挑战：包括焦点转移现象、对齐陈述与正确引用所需的复杂推理，以及检索文档精度与广度之间的权衡困境。本文提出VTG——一种融合演化记忆与自反思机制的可验证文本生成创新框架。VTG引入演化式长短时记忆模块，用以同时保留高价值文档与近期文档。框架配备包含证据定位器的双层验证器，用于对陈述与引用间的关联进行重新思考与反思。此外，通过主动检索与多样化查询生成策略，有效提升了检索文档的精度与广度。我们在三项知识密集型任务的五个数据集上进行了广泛实验，结果表明VTG显著优于现有基线方法。