As large language models continue to develop in the field of AI, text generation systems are susceptible to a worrisome phenomenon known as hallucination. In this study, we summarize recent compelling insights into hallucinations in LLMs. We present a novel taxonomy of hallucinations from various text generation tasks, thus provide theoretical insights, detection methods and improvement approaches. Based on this, future research directions are proposed. Our contribution are threefold: (1) We provide a detailed and complete taxonomy for hallucinations appearing in text generation tasks; (2) We provide theoretical analyses of hallucinations in LLMs and provide existing detection and improvement methods; (3) We propose several research directions that can be developed in the future. As hallucinations garner significant attention from the community, we will maintain updates on relevant research progress.

翻译：随着大型语言模型在人工智能领域的持续发展，文本生成系统容易出现一种被称为"幻觉"的令人担忧的现象。本研究总结了近期关于大型语言模型中幻觉问题的深刻见解。我们针对各类文本生成任务提出了一种新颖的幻觉分类体系，并从理论视角、检测方法及改进方案三个维度展开论述。在此基础上，我们提出了未来研究方向。本研究的贡献体现在三方面：（1）为文本生成任务中出现的幻觉现象提供了详尽完整的分类体系；（2）对大型语言模型中的幻觉现象进行了理论分析，并系统梳理了现有检测与改进方法；（3）提出了若干值得未来持续推进的研究方向。鉴于幻觉问题已引起学界广泛关注，我们将持续更新相关研究进展。