大模型在开放世界下幻觉不可避免，应视为需兼容人类智能的结构性特征。
Hallucination is Inevitable for LLMs with the Open World Assumption
- 将幻觉视为泛化问题，在封闭世界可缓解，开放世界则必然出现
- 提出幻觉分类：可纠正与不可避免两类，后者在开放世界中无法消除
- 建议从工程缺陷转向结构性特征看待幻觉，适配人类认知模式
大语言模型虽具备出色的语言能力，但常产生不准确或虚构内容，即所谓“幻觉”。工程方法通常将幻觉视为需最小化的缺陷，而形式分析则认为其具有理论必然性。然而，这两种观点在实现人工通用智能（AGI）所需条件下仍不完整。本文将“幻觉”重新定义为泛化问题的表现。在封闭世界假设下（训练与测试分布一致），幻觉可被缓解；但在开放世界假设下（环境无边界），幻觉成为必然结果。本文进一步构建了幻觉分类体系，区分可纠正与在开放世界条件下看似不可避免的类型。在此基础上，提出应将幻觉不仅视为工程缺陷，更应作为需容忍并兼容人类智能的结构性特征来对待。
原文摘要 · Abstract (English)
Large Language Models (LLMs) exhibit impressive linguistic competence but also produce inaccurate or fabricated outputs, often called ``hallucinations''. Engineering approaches usually regard hallucination as a defect to be minimized, while formal analyses have argued for its theoretical inevitability. Yet both perspectives remain incomplete when considering the conditions required for artificial general intelligence (AGI). This paper reframes ``hallucination'' as a manifestation of the generalization problem. Under the Closed World assumption, where training and test distributions are consistent, hallucinations may be mitigated. Under the Open World assumption, however, where the environment is unbounded, hallucinations become inevitable. This paper further develops a classification of hallucination, distinguishing cases that may be corrected from those that appear unavoidable under open-world conditions. On this basis, it suggests that ``hallucination'' should be approached not merely as an engineering defect but as a structural feature to be tolerated and made compatible with human intelligence.
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。