系统梳理大模型幻觉的成因、检测与防控，构建全生命周期框架。
Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention
- 按数据、训练、推理三阶段分类幻觉，对应生命周期。
- 提出多维度评估基准，助力识别与控制幻觉。
- 适合安全、医疗等领域研究者参考，提升模型可靠性。
大模型幻觉的生命周期概念有助于在医疗、法律和科研等高风险场景中建立可靠的模型控制体系。现有综述多聚焦于幻觉检测或缓解，本文则首次提出基于生命周期的全面分析框架，将幻觉分为数据相关、训练相关和推理相关三类，分别探讨其成因、检测方法及应对策略。同时，针对多个基准数据集进行参数化评估，以判断其在幻觉识别、限制与管理中的适用性。该综述为研究人员和实践者提供标准化工具，实现对幻觉的系统化诊断与治理，推动更安全、可靠的大型语言模型建设。
原文摘要 · Abstract (English)
The lifecycle of hallucination in LLMs is a concept that enables building solid frameworks on the control and reliability of LLMs in high-stakes environments, including health, legal, and scientific research. Although previous surveys have primarily focused on detection or mitigation, this survey provides a lifecycle-based overview of the hallucinations in the LLMs, their cause, detection, mitigation, and prevention.We propose a three-fold categorization of hallucinations across the LLM lifecycle: data-related, training-related, and inference-related, which is consistent with the lifecycle of the development of the LLM. Each of these stages is discussed regarding the cause of hallucinations, their detection, and the ways they can be addressed under specific mitigation or prevention interventions. In addition, we discuss the available benchmark data using a number of parameters so as to establish their suitability in identifying, restricting and managing hallucinations. The survey provides researchers and practitioners with a standardized framework to understand, diagnose, and cure hallucinations in a systematic system to present actionable data to build safer and more reliable LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。