系统梳理大模型幻觉成因与机制，助力提升生成可靠性
Review of Hallucination Understanding in Large Language and Vision Models
- 构建图文模型幻觉的多层级统一框架，减少理解碎片化
- 发现幻觉多源于数据分布规律与模型固有偏见
- 适合关注AI可靠性、安全性的研究者与开发者
大型语言与视觉模型在实际应用中的广泛使用，使得应对幻觉问题——即模型生成错误或无意义内容——变得尤为迫切。这类错误可能在部署中传播虚假信息，造成财务与运营损失。尽管已有大量研究致力于缓解幻觉，但对其本质的理解仍不完整且分散。缺乏连贯认知可能导致解决方案仅针对表象而非根本原因，从而限制其有效性与泛化能力。为此，本文提出一个跨任务、跨模态的统一多层级框架，用于刻画各类应用场景下的图文幻觉，以减少概念碎片化。进一步采用任务-模态交错分析方法，将幻觉与模型生命周期中的具体机制关联，揭示其常源于可预测的数据分布模式与继承性偏见。通过深化对幻觉成因的理解，本综述为开发更稳健、有效的生成式AI系统解决方案奠定基础。
原文摘要 · Abstract (English)
The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrect or nonsensical outputs. These errors can propagate misinformation during deployment, leading to both financial and operational harm. Although much research has been devoted to mitigating hallucinations, our understanding of it is still incomplete and fragmented. Without a coherent understanding of hallucinations, proposed solutions risk mitigating surface symptoms rather than underlying causes, limiting their effectiveness and generalizability in deployment. To tackle this gap, we first present a unified, multi-level framework for characterizing both image and text hallucinations across diverse applications, aiming to reduce conceptual fragmentation. We then link these hallucinations to specific mechanisms within a model's lifecycle, using a task-modality interleaved approach to promote a more integrated understanding. Our investigations reveal that hallucinations often stem from predictable patterns in data distributions and inherited biases. By deepening our understanding, this survey provides a foundation for developing more robust and effective solutions to hallucinations in real-world generative AI systems.
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。