系统梳理大模型幻觉成因与应对策略，助力可信AI落地
Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models
- 按成因、检测、解决方案三维度系统分类
- 揭示幻觉背后的认知与信息不对称机制
- 适合关注大模型可靠性与安全性的研究者
尽管大语言模型具备出色的语言生成能力，但其常产生看似合理实则虚构的内容，即‘幻觉’。此类现象在金融、法律、医疗等领域可能导致重大经济损失、法律纠纷和健康风险。本文系统梳理了大模型幻觉的成因、检测方法与缓解策略，特别聚焦于幻觉根源分析及现有技术的有效性评估，旨在揭示其内在逻辑，推动更高效、创新的应对方案发展，为构建可信大模型提供全面支撑。
原文摘要 · Abstract (English)
Edgar Allan Poe noted, "Truth often lurks in the shadow of error," highlighting the deep complexity intrinsic to the interplay between truth and falsehood, notably under conditions of cognitive and informational asymmetry. This dynamic is strikingly evident in large language models (LLMs). Despite their impressive linguistic generation capabilities, LLMs sometimes produce information that appears factually accurate but is, in reality, fabricated, an issue often referred to as 'hallucinations'. The prevalence of these hallucinations can mislead users, affecting their judgments and decisions. In sectors such as finance, law, and healthcare, such misinformation risks causing substantial economic losses, legal disputes, and health risks, with wide-ranging consequences.In our research, we have methodically categorized, analyzed the causes, detection methods, and solutions related to LLM hallucinations. Our efforts have particularly focused on understanding the roots of hallucinations and evaluating the efficacy of current strategies in revealing the underlying logic, thereby paving the way for the development of innovative and potent approaches. By examining why certain measures are effective against hallucinations, our study aims to foster a comprehensive approach to tackling this issue within the domain of 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。