mlsanityData to 14 Oct 2026

A Categorical Analysis of Large Language Models and Why LLMs Circumvent the Symbol Grounding Problem

arXiv 2512.09117 ↗First posted 9 Dec 2025cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper presents a formal, categorical framework for analysing how humans and large language models (LLMs) transform content into truth-evaluated propositions about a state space of possible worlds W , in order to argue that LLMs do not solve but circumvent the symbol grounding problem.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 22 of its 64 references that are in the map. First posted on arXiv 9 Dec 2025.

Builds on

22 of 64 references.

References · 22

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  3. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  4. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  5. 2020Experience Grounds Languagecited by 242
  6. 2023Grounding Large Language Models in Interactive Environments with Online Reinforcement Learningcited by 195
  7. 2023A Categorical Archive of ChatGPT Failurescited by 168
  8. 2022Meaning without reference in large language modelscited by 76
  9. 2023The Vector Grounding Problemcited by 39
  10. 2025Provable Separations between Memorization and Generalization in Diffusion Modelscited by 14
  11. 2024A Survey of Automatic Hallucination Evaluation on Natural Language Generationcited by 7
  12. 2024Transforming Agency. On the mode of existence of Large Language Modelscited by 7
10 more
  1. 2020Categorical Stochastic Processes and Likelihoodcited by 6
  2. 2025The Mechanistic Emergence of Symbol Grounding in Language Modelscited by 6
  3. 2017Knowledge Representation in Bicategories of Relationscited by 4
  4. 2024Category-Theoretical and Topos-Theoretical Frameworks in Machine Learning: A Surveycited by 3
  5. 2025OracleAgent: A Multimodal Reasoning Agent for Oracle Bone Script Researchcited by 3
  6. 2025Forget BIT, It is All about TOKEN: Towards Semantic Information Theory for LLMscited by 3
  7. 2019Notes on Category Theory with examples from basic mathematicscited by 2
  8. 2024A Roadmap for Embodied and Social Grounding in LLMscited by 2
  9. 2025A Rose by Any Other Name Would Smell as Sweet: Categorical Homotopy Theory for Large Language Modelscited by 1
  10. 2025Higher-Order Regularization Learning on Hypergraphscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Can We Predict Before Executing Machine Learning Agents?cited by 10
  2. 2026LLMs Don't Pay for the Jumpcited by 1
  3. 2026The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agentscited by 0