The Concept of Representation in ML: Beyond Plato and Aristotle

• URL: http://arxiv.org/abs/2607.17800v1
• Date: Mon, 20 Jul 2026 10:35:48 GMT
• Title: The Concept of Representation in ML: Beyond Plato and Aristotle
• Abstract summary: We argue that recent claims about the convergence of representational properties across different AI models are driven by a unified structure of reality.<n>In particular, we assess the arguments developed in The Platonic Representation Hypothesis, according to which this convergence is driven by a unified structure of reality.<n>We argue that these philosophical resources can clarify what is at stake in such claims, explain why alignment evidence alone is insufficient for strong metaphysical conclusions, and suggest directions for future research.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Representation is a central concept in modern machine learning, where it usually refers to internal encodings that support learning and generalization. As models scale and their capabilities become increasingly human-level, this representational language sometimes shifts from an engineering context into the more philosophically loaded domain of mental representation. We argue that this is the case for recent claims about the convergence of representational properties across different AI models. In particular, we assess the arguments developed in The Platonic Representation Hypothesis, according to which this convergence is driven by a unified structure of reality. We examine this claim by introducing arguments and ideas from debates about mental representation in the philosophy of mind. We argue that these philosophical resources can clarify what is at stake in such claims, explain why alignment evidence alone is insufficient for strong metaphysical conclusions, and suggest directions for future research.

Related papers

• Epistemoverse: Toward an AI-Driven Knowledge Metaverse for Intellectual Heritage Preservation [0.0]
  We analyze authentic philosophical debates generated among AI-reincarnated philosophers within the interactive art installations of the Syntropic Counterpoints project.<n>We propose the concept of the Epistemoverse--a metaverse of knowledge where human and machine cognition intersect to preserve, reinterpret, and extend intellectual heritage through AI-driven interaction.
  arXiv  Detail & Related papers  (2025-12-13T06:18:50Z)
• Function Alignment: A New Theory of Mind and Intelligence, Part I: Foundations [0.0]
  This paper introduces function alignment, a novel theory of mind and intelligence.<n>It explicitly models how meaning, interpretation, and analogy emerge from interactions among layered representations.<n>It bridges disciplines often kept apart, linking computational architecture, psychological theory, and even contemplative traditions such as Zen.
  arXiv  Detail & Related papers  (2025-03-27T02:59:01Z)
• Revealing emergent human-like conceptual representations from language prediction [90.73285317321312]
  Large language models (LLMs) trained solely through next-token prediction on text exhibit strikingly human-like behaviors.<n>Are these models developing concepts akin to those of humans?<n>We found that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts.
  arXiv  Detail & Related papers  (2025-01-21T23:54:17Z)
• A Complexity-Based Theory of Compositionality [53.025566128892066]
  In AI, compositional representations can enable a powerful form of out-of-distribution generalization.<n>Here, we propose a definition, which we call representational compositionality, that accounts for and extends our intuitions about compositionality.<n>We show how it unifies disparate intuitions from across the literature in both AI and cognitive science.
  arXiv  Detail & Related papers  (2024-10-18T18:37:27Z)
• Understanding XAI Through the Philosopher's Lens: A Historical Perspective [5.839350214184222]
  We show that a gradual progression has independently occurred in both domains from logicaldeductive to statistical models of explanation. Similar concepts have independently emerged in both such as, for example, the relation between explanation and understanding and the importance of pragmatic factors.
  arXiv  Detail & Related papers  (2024-07-26T14:44:49Z)
• Conceptual and Unbiased Reasoning in Language Models [98.90677711523645]
  We propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions. We show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks. We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making.
  arXiv  Detail & Related papers  (2024-03-30T00:53:53Z)
• From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought [124.40905824051079]
  We propose rational meaning construction, a computational framework for language-informed thinking. We frame linguistic meaning as a context-sensitive mapping from natural language into a probabilistic language of thought. We show that LLMs can generate context-sensitive translations that capture pragmatically-appropriate linguistic meanings. We extend our framework to integrate cognitively-motivated symbolic modules.
  arXiv  Detail & Related papers  (2023-06-22T05:14:00Z)
• On the Computation of Meaning, Language Models and Incomprehensible Horrors [0.0]
  We integrate foundational theories of meaning with a mathematical formalism of artificial general intelligence (AGI) Our findings shed light on the relationship between meaning and intelligence, and how we can build machines that comprehend and intend meaning.
  arXiv  Detail & Related papers  (2023-04-25T09:41:00Z)
• Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models [86.25460882547581]
  We introduce the PHYsical Concepts Inference NEtwork (PHYCINE), a system that infers physical concepts in different abstract levels without supervision. We show that object representations containing the discovered physical concepts variables could help achieve better performance in causal reasoning tasks.
  arXiv  Detail & Related papers  (2023-03-03T11:52:21Z)
• What does it mean to represent? Mental representations as falsifiable memory patterns [8.430851504111585]
  We argue that causal and teleological approaches fail to provide a satisfactory account of representation. We sketch an alternative according to which representations correspond to inferred latent structures in the world. These structures are assumed to have certain properties objectively, which allows for planning, prediction, and detection of unexpected events.
  arXiv  Detail & Related papers  (2022-03-06T12:52:42Z)
• Formalising Concepts as Grounded Abstractions [68.24080871981869]
  This report shows how representation learning can be used to induce concepts from raw data. The main technical goal of this report is to show how techniques from representation learning can be married with a lattice-theoretic formulation of conceptual spaces.
  arXiv  Detail & Related papers  (2021-01-13T15:22:01Z)

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.