# What does it mean to understand language?

arXiv: https://arxiv.org/abs/2511.19757 · HTML: https://mlsanity.com/paper/2511.19757/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 132 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023)
- [Meaning without reference in large language models](https://mlsanity.com/paper/2208.02957/) (2022)
- [Scaling laws for language encoding models in fMRI](https://mlsanity.com/paper/2305.11863/) (2023)
- [The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units](https://mlsanity.com/paper/2411.02280/) (2024)
- [From Language to Cognition: How LLMs Outgrow the Human Language Network](https://mlsanity.com/paper/2503.01830/) (2025)
- [Are formal and functional linguistic mechanisms dissociated in language models?](https://mlsanity.com/paper/2503.11302/) (2025)
- [Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization](https://mlsanity.com/paper/2506.13331/) (2025)
- [Generative causal testing to bridge data-driven models and scientific theories in language neuroscience](https://mlsanity.com/paper/2410.00812/) (2024)
- [LITcoder: A General-Purpose Library for Building and Comparing Encoding Models](https://mlsanity.com/paper/2509.09152/) (2025)
- [Modeling the language cortex with form-independent and enriched representations of sentence meaning reveals remarkable semantic abstractness](https://mlsanity.com/paper/2510.02354/) (2025)
- [Evaluating Contrast Localizer for Identifying Causal Units in Social & Mathematical Tasks in Language Models](https://mlsanity.com/paper/2508.08276/) (2025)
- [Neural Hardware for the Language of Thought: New Rules for an Old Game](https://mlsanity.com/paper/2510.10251/) (2025)

## Abstract (arXiv)

Language understanding entails not just extracting the surface-level meaning of the linguistic input, but constructing rich mental models of the situation it describes. Here we propose that because processing within the brain's core language system is fundamentally limited, deeply understanding language requires exporting information from the language system to other brain regions that compute perceptual and motor representations, construct mental models, and store our world knowledge and autobiographical memories. We review the existing evidence for this hypothesis, and argue that recent progress in cognitive neuroscience provides both the conceptual foundation and the methods to directly test it, thus opening up a new strategy to reveal what it means, cognitively and neurally, to understand language.