# Language Writ Large: LLMs, ChatGPT, Grounding, Meaning and Understanding

arXiv: https://arxiv.org/abs/2402.02243 · HTML: https://mlsanity.com/paper/2402.02243/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 22 references that are in the map.
- First posted on arXiv 3 Feb 2024.

## Builds on (most cited first, 5 of 5)

- [Deep Reinforcement Learning and its Neuroscientific Implications](https://mlsanity.com/paper/2007.03750/) (2020)
- [The Latent Structure of Dictionaries](https://mlsanity.com/paper/1411.0129/) (2014)
- [Categorical Perception: A Groundwork for Deep Learning](https://mlsanity.com/paper/2012.05549/) (2020)
- [Learning-induced categorical perception in a neural network model](https://mlsanity.com/paper/1805.04567/) (2018)
- [Category learning can alter perception and its neural correlates](https://mlsanity.com/paper/1805.04619/) (2018)

## Built on by (most cited first, 12 of 12)

- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Monotonic Representation of Numeric Properties in Language Models](https://mlsanity.com/paper/2403.10381/) (2024)
- [NTSEBENCH: Cognitive Reasoning Benchmark for Vision Language Models](https://mlsanity.com/paper/2407.10380/) (2024)
- [Large language models and linguistic intentionality](https://mlsanity.com/paper/2404.09576/) (2024)
- [Evaluating Large Language Models for Structured Science Summarization in the Open Research Knowledge Graph](https://mlsanity.com/paper/2405.02105/) (2024)
- [Reasoning about Affordances: Causal and Compositional Reasoning in LLMs](https://mlsanity.com/paper/2502.16606/) (2025)
- [Proprioception Enhances Vision Language Model in Generating Captions and Subtask Segmentations for Robot Task](https://mlsanity.com/paper/2512.20876/) (2025)
- [Spilled Energy in Large Language Models](https://mlsanity.com/paper/2602.18671/) (2026)
- [Computational Thought Experiments for a More Rigorous Philosophy and Science of the Mind](https://mlsanity.com/paper/2405.08304/) (2024)
- [Generative AI, Pragmatics, and Authenticity in Second Language Learning](https://mlsanity.com/paper/2410.14395/) (2024)
- [Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs](https://mlsanity.com/paper/2508.11068/) (2025)
- [Detecting Soft Skills in ML Engineering Roles CVs](https://mlsanity.com/paper/2608.10046/) (2026)

## Abstract (arXiv)

Apart from what (little) OpenAI may be concealing from us, we all know (roughly) how ChatGPT works (its huge text database, its statistics, its vector representations, and their huge number of parameters, its next-word training, and so on). But none of us can say (hand on heart) that we are not surprised by what ChatGPT has proved to be able to do with these resources. This has even driven some of us to conclude that ChatGPT actually understands. It is not true that it understands. But it is also not true that we understand how it can do what it can do. I will suggest some hunches about benign biases: convergent constraints that emerge at LLM scale that may be helping ChatGPT do so much better than we would have expected. These biases are inherent in the nature of language itself, at LLM scale, and they are closely linked to what it is that ChatGPT lacks, which is direct sensorimotor grounding to connect its words to their referents and its propositions to their meanings. These convergent biases are related to (1) the parasitism of indirect verbal grounding on direct sensorimotor grounding, (2) the circularity of verbal definition, (3) the mirroring of language production and comprehension, (4) iconicity in propositions at LLM scale, (5) computational counterparts of human categorical perception in category learning by neural nets, and perhaps also (6) a conjecture by Chomsky about the laws of thought. The exposition will be in the form of a dialogue with ChatGPT-4.