Ceci n'est pas une pipe: AI systems as semantic abstractions
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Machine-Learning Compositional Study of Exoplanetary Material Accreted Onto Five Helium-Atmosphere White Dwarfs with $\texttt{cecilia}$
We present the first application of the Machine Learning (ML) pipeline $\texttt{cecilia}$ to determine the physical parameters and photospheric composition of five metal-polluted He-atmosphere white dwarfs without well-c…
cecilia: A Machine Learning-Based Pipeline for Measuring Metal Abundances of Helium-rich Polluted White Dwarfs
Over the past several decades, conventional spectral analysis techniques of polluted white dwarfs have become powerful tools to learn about the geology and chemistry of extrasolar bodies. Despite their proven capabilitie…
Efficient Neural NetworkGeochemistryBelief Scene Graphs: Expanding Partial Scenes with Objects through Computation of Expectation
In this article, we propose the novel concept of Belief Scene Graphs, which are utility-driven extensions of partial 3D scene graphs, that enable efficient high-level task planning with partial information. We propose a …
Common Sense ReasoningTask PlanningCECILIA: Comprehensive Secure Machine Learning Framework
Since ML algorithms have proven their success in many different applications, there is also a big interest in privacy preserving (PP) ML methods for building models on sensitive data. Moreover, the increase in the number…
BIG-bench Machine LearningPrivacy PreservingPerception for Autonomous Systems (PAZ)
In this paper we introduce the Perception for Autonomous Systems (PAZ) software library. PAZ is a hierarchical perception library that allow users to manipulate multiple levels of abstraction in accordance to their requi…
2D Object Detection6D Pose EstimationData AugmentationEmotion Classification+7