发表机构
ARM; UCL; NYU(安谋科技; 伦敦大学学院; 纽约大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
研究人工智能系统输出为设计表示的问题,提出语义框架描述该系统以检查表示正确性,区分相关内容并定义常见故障,有望为指定和检查人工智能系统提供有用词汇表。
AI 中文摘要
人工智能系统的输出并非它看似描述的事实或世界状态,而是一种经过设计的表示。我们提出了一个语义框架来描述人工智能系统,以便能够检查这种表示的正确性。为此,我们区分了由公认的领域知识证明合理的内容、参考来源所说的内容以及系统当前可以使用的内容。这使我们能够为常见故障给出精确的定义:外推、被驳斥或无根据的断言、来源与知识不匹配、过时或被驳斥的来源、添加的假设、无根据的使用……我们希望我们的框架能为指定和检查人工智能系统提供一个有用的词汇表,其输出、引用、工具调用和改变世界的行动必须由可靠的主张和明确的权威来证明,而不是表面上的流畅性。
英文摘要
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.