Ceci n'est pas une pipe: AI systems as semantic abstractions

• URL: http://arxiv.org/abs/2607.09489v1
• Date: Fri, 10 Jul 2026 15:05:28 GMT
• Title: Ceci n'est pas une pipe: AI systems as semantic abstractions
• Abstract summary: An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation.<n>We propose a semantic framework to describe AI systems, to be able to examine the correctness of such representations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Semantic Knowledge Technologies: what the Semantic Web lost sight of, and what it never had [0.0]
  The Semantic Web set out to give information a machine-interpretable form so that software could integrate and reason over it.<n>Its standards became scientific knowledge infrastructure, but the machine competence it promised did not follow.<n>This paper argues the original goal was right and the technical programme incomplete.
  arXiv  Detail & Related papers  (2026-09-12T19:55:46Z)
• Radical AI Interpretability [0.0]
  We develop a framework for interpreting AI systems as agents.<n>We draw on the philosophical tradition of radical interpretation and the tools of mechanistic interpretability.
  arXiv  Detail & Related papers  (2026-06-25T01:58:38Z)
• Limitations on Safe, Trusted, Artificial General Intelligence [14.425238904385074]
  Safety, trust and Artificial General Intelligence (AGI) are aspirational goals in artificial intelligence (AI) systems.<n>We propose strict, mathematical definitions of safety, trust, and AGI.<n>We show our results for program verification, planning, and graph reachability.
  arXiv  Detail & Related papers  (2025-09-25T22:16:38Z)
• Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models [57.834711966432685]
  Bullshit, as conceptualized by philosopher Harry Frankfurt, refers to statements made without regard to their truth value.<n>We introduce the Bullshit Index, a novel metric quantifying large language model's indifference to truth.<n>We observe prevalent machine bullshit in political contexts, with weasel words as the dominant strategy.
  arXiv  Detail & Related papers  (2025-07-10T07:11:57Z)
• Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding [40.78154629252038]
  Forcing binary labels upon ambiguous claims lowers the reliability of evaluation.<n>We introduce LLM-generated edits of summaries as a method of providing a nuanced evaluation of claims.<n>We show that ARM produces a absolute 21% improvement in annotator agreement on claim faithfulness.
  arXiv  Detail & Related papers  (2025-04-01T19:08:24Z)
• Honesty Is the Best Policy: Defining and Mitigating AI Deception [26.267047631872366]
  We focus on the problem that agents might deceive in order to achieve their goals. We introduce a formal definition of deception in structural causal games. We show, experimentally, that these results can be used to mitigate deception in reinforcement learning agents and language models.
  arXiv  Detail & Related papers  (2023-12-03T11:11:57Z)
• Taming AI Bots: Controllability of Neural States in Large Language Models [81.1573516550699]
  We first introduce a formal definition of meaning'' that is amenable to analysis. We then characterize meaningful data'' on which large language models (LLMs) are ostensibly trained. We show that, when restricted to the space of meanings, an AI bot is controllable.
  arXiv  Detail & Related papers  (2023-05-29T03:58:33Z)
• Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models [64.58271886337826]
  We study ambiguities that arise in text-to-image generative models. We propose a framework to mitigate ambiguities in the prompts given to the systems by soliciting clarifications from the user.
  arXiv  Detail & Related papers  (2022-11-17T17:12:43Z)
• Improving Wikipedia Verifiability with AI [116.69749668874493]
  We develop a neural network based system, called Side, to identify Wikipedia citations that are unlikely to support their claims. Our first citation recommendation collects over 60% more preferences than existing Wikipedia citations for the same top 10% most likely unverifiable claims. Our results indicate that an AI-based system could be used, in tandem with humans, to improve the verifiability of Wikipedia.
  arXiv  Detail & Related papers  (2022-07-08T15:23:29Z)
• On Nested Justification Systems (full version) [13.76408511310322]
  Nested justification systems, first introduced by Denecker et al., allow for the composition of justification systems. We show in this paper that the original semantics for nested justification systems lead to the loss of information relevant for explanations. Furthermore, we show how nested justification systems allow representing fixpoint definitions.
  arXiv  Detail & Related papers  (2022-05-09T20:23:22Z)
• Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand? [87.20342701232869]
  We investigate the abilities of ungrounded systems to acquire meaning. We study whether assertions enable a system to emulate representations preserving semantic relations like equivalence. We find that assertions enable semantic emulation if all expressions in the language are referentially transparent. However, if the language uses non-transparent patterns like variable binding, we show that emulation can become an uncomputable problem.
  arXiv  Detail & Related papers  (2021-04-22T01:00:17Z)
• This is not the Texture you are looking for! Introducing Novel Counterfactual Explanations for Non-Experts using Generative Adversarial Learning [59.17685450892182]
  counterfactual explanation systems try to enable a counterfactual reasoning by modifying the input image. We present a novel approach to generate such counterfactual image explanations based on adversarial image-to-image translation techniques. Our results show that our approach leads to significantly better results regarding mental models, explanation satisfaction, trust, emotions, and self-efficacy than two state-of-the art systems.
  arXiv  Detail & Related papers  (2020-12-22T10:08:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.