AI输出是设计的表示而非真实世界，该研究提出语义框架验证其可靠性。
Ceci n'est pas une pipe: AI systems as semantic abstractions
- 区分领域知识、引用来源与系统可用信息，构建验证框架
- 精准定义外推、断言无效、来源不匹配等常见错误类型
- 适合需严格验证输出可信度的AI应用开发者与审核者
AI系统的输出并非其所描述的事实或世界状态，而是一种工程化表示。本文提出一种语义框架，用于描述和检验这些表示的正确性。该框架明确区分经认可的领域知识、引用来源的内容，以及系统当前可使用的依据。基于此，可对常见错误进行精确界定：如外推、被驳回或无支持的断言、来源与知识不一致、过时或已被驳回的来源、新增假设、无支持的使用等。我们希望该框架为需要可靠主张和明确权威性的AI系统（包括其引用、工具调用及影响世界的行动）提供一套有用的术语体系，以替代仅凭流畅表达的判断方式。
原文摘要 · Abstract (English)
An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation. We propose a semantic framework to describe AI systems, to be able to examine the correctness of such representations. To do so, we distinguish what is justified by accepted domain knowledge, what reference sources say, and what the system can currently use. This allows us to give precise definitions to common failures: extrapolation, refuted or unsupported assertion, sources versus knowledge mismatch, stale or refuted source, added hypotheses, unsupported use... We hope our framework gives a useful vocabulary for specifying and checking AI systems whose outputs, citations, tool calls, and world-changing actions must be justified by reliable claims and explicit authority rather than apparent fluency.
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。