大语言模型（Large Language Models, LLMs）中的幻觉指生成的内容不符合输入信息或现实世界事实。本文对大语言模型的幻觉问题展开严谨研究，包含形式化定义与理论分析。我们区分了内在幻觉与外在幻觉，并定义了模型的“幻觉风险”。我们利用学习理论框架（PAC-Bayes与Rademacher复杂度）推导了该风险的边界。随后我们调研了幻觉检测策略，例如token级不确定性估计、置信度校准以及注意力对齐检查。在缓解方法方面，我们讨论了检索增强生成、幻觉感知微调、logit校准以及事实验证模块整合等方案。我们提出了一套统一的检测与缓解工作流程，并辅以示意图说明以整合这些策略。最后，我们概述了幻觉的评估协议，推荐了用于量化并减少幻觉的数据集、指标与实验设置。本研究为解决大语言模型幻觉这一关键挑战奠定了理论基础并提供了实践指南。
英文摘要：
Hallucination in Large Language Models (LLMs) refers to the generation of content that is not faithful to the input or the real-world facts. This paper provides a rigorous treatment of hallucination in LLMs, including formal definitions and theoretical analyses. We distinguish between intrinsic and extrinsic hallucinations, and define a \textit{hallucination risk} for models. We derive bounds on this risk using learning-theoretic frameworks (PAC-Bayes and Rademacher complexity). We then survey detection strategies for hallucinations, such as token-level uncertainty estimation, confidence calibration, and attention alignment checks. On the mitigation side, we discuss approaches including retrieval-augmented generation, hallucination-aware fine-tuning, logit calibration, and the incorporation of fact-verification modules. We propose a unified detection and mitigation workflow, illustrated with a diagram, to integrate these strategies. Finally, we outline evaluation protocols for hallucination, recommending datasets, metrics, and experimental setups to quantify and reduce hallucinations. Our work lays a theoretical foundation and practical guidelines for addressing the crucial challenge of hallucination in LLMs.
Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems
Electronic Information School, Wuhan University（武汉大学电子信息学院）；School of Computing, Dublin City University（都柏林城市大学计算机学院）；School of Public Health, Wuhan University（武汉大学公共卫生学院）；Insight Centre for Data Analytics, University of Galway（Galway大学数据分析研究中心）；Insight Centre for Data Analytics, Dublin City University（都柏林城市大学数据分析研究中心）
An Evolutionary Large Language Model for Hallucination Mitigation
BIOSTIM Laboratory Faculty of Medicine Salah Boubnider University Constantine, Algeria（BIOSTIM实验室医学院萨拉赫·布宾德大学阿尔及利亚科纳克特）；Department of IFA Faculty of NTIC Abdelhamid Mehri University Constantine, Algeria（IFA部门NTIC学院阿卜杜勒哈米德·梅赫里大学阿尔及利亚科纳克特）
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
City University of Hong Kong（香港城市大学）；National University of Singapore（新加坡国立大学）；Shanghai Jiao Tong University（上海交通大学）；Stanford University（斯坦福大学）；Penn State University（宾夕法尼亚州立大学）；Hong Kong University of Science and Technology（香港科技大学）
A Concise Review of Hallucinations in LLMs and their Mitigation
Computer Engineering K J Somaiya Institute of Technology Mumbai, India；Data Science K J Somaiya Institute of Technology Mumbai, India；Information Technology K J Somaiya Institute of Technology Mumbai, India
HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
Xin Tong School of Information and Cyber Security People’s Public Security University of China（信息与网络安全学院 中国人民公安大学）；Zhi Lin School of Safety Science Tsinghua University（安全科学学院 清华大学）；Jingya Wang School of Information and Cyber Security People’s Public Security University of China（信息与网络安全学院 中国人民公安大学）；Bo Jin* The Third Research Institute of the Ministry of Public Security of China（公安部第三研究所）
MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning
Shenzhen Key Laboratory for High Performance Data Mining（深圳高性能数据挖掘重点实验室）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology（深圳先进技术大学人工智能研究院）
Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor
College of Computer Science, Nankai University（南开大学计算机科学学院）；Haihe Lab of ITAI College of intelligent Science and Technology, Inner Mongolia University of Technology（内蒙古工业大学智能科学与技术学院海河实验室）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Department of Electrical and Computer Engineering, Stony Brook University（石溪大学电气与计算机工程系）；Department of Computer Science, Michigan Technological University（密歇根技术大学计算机科学系）
On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China（中国科学院软件研究所信息处理实验室，北京，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）；Xiaohongshu Inc（小红书公司）
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences（自动化研究所人工智能与自然语言处理实验室，中国科学院）；School of Artificial Intelligence, UCAS（中国科学院大学人工智能学院）；Meituan（美团）
GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Peking University（北京大学）；Southwest Jiaotong University（西南交通大学）；Shanghai Jiaotong University（上海交通大学）；Chinese University of Hong Kong（香港中文大学）
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University)（东南大学新一代人工智能技术及其交叉应用关键实验室）；Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Wuhan University of Technology（武汉理工大学）；National University of Singapore（新加坡国立大学）
