mlsanityData to 14 Oct 2026

What Do Large Language Models Know? Tacit Knowledge as a Potential Causal-Explanatory Structure

arXiv 2504.12187 ↗First posted 16 Apr 2025cs.CL cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

It is sometimes assumed that Large Language Models (LLMs) know language, or for example that they know that Paris is the capital of France. But what -- if anything -- do LLMs actually know? In this paper, I argue that LLMs can acquire tacit knowledge as defined by Martin Davies (1990). Whereas Davies himself denies that neural networks can acquire tacit knowledge, I demonstrate that certain architectural features of LLMs satisfy the constraints of semantic description, syntactic structure, and causal systematicity. Thus, tacit knowledge may serve as a conceptual framework for describing, explaining, and intervening on LLMs and their behavior.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 15 of its 51 references that are in the map. First posted on arXiv 16 Apr 2025.

Builds on

15 of 51 references.

References · 15

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  4. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,336
  5. 2022Toy Models of Superpositioncited by 971
  6. 2021Editing Factual Knowledge in Language Modelscited by 553
  7. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  8. 2022Talking About Large Language Modelscited by 175
  9. 2021Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Colorcited by 119
  10. 2020Syntactic Structure from Deep Learningcited by 99
  11. 2022The Geometry of Multilingual Language Model Representationscited by 95
  12. 2019Augmenting Self-attention with Persistent Memorycited by 93
3 more
  1. 2021Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefscited by 79
  2. 2022Meaning without reference in large language modelscited by 76
  3. 2023From task structures to world models: What do LLMs know?cited by 46

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025Mechanistic Interpretability Needs Philosophycited by 6
  2. 2026Tacit Coordination of Large Language Modelscited by 5
  3. 2025Morality in AI. A plea to embed morality in LLM architectures and frameworkscited by 0
  4. 2025Artificial Intelligence and Nuclear Weapons Proliferation: The Technological Arms Race for (In)visibilitycited by 0
  5. 2026Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspectivecited by 0
  6. 2026Where Polanyi Meets Galois: Tacit Knowing as an Algebro-Deterministic Operation, Toward Re-rooting AI-Generated Sciencecited by 0