# From Language to Cognition: How LLMs Outgrow the Human Language Network

arXiv: https://arxiv.org/abs/2503.01830 · HTML: https://mlsanity.com/paper/2503.01830/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 84 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [WinoGrande: An Adversarial Winograd Schema Challenge at Scale](https://mlsanity.com/paper/1907.10641/) (2019)
- [A Review on Language Models as Knowledge Bases](https://mlsanity.com/paper/2204.06031/) (2022)
- [Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?](https://mlsanity.com/paper/2212.12131/) (2022)
- [Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs](https://mlsanity.com/paper/1909.06161/) (2019)
- [Recurrence is required to capture the representational dynamics of the human visual system](https://mlsanity.com/paper/1903.05946/) (2019)
- [Neural Redshift: Random Networks are not Random Functions](https://mlsanity.com/paper/2403.02241/) (2024)
- [The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units](https://mlsanity.com/paper/2411.02280/) (2024)
- [Task-Driven Convolutional Recurrent Models of the Visual System](https://mlsanity.com/paper/1807.00053/) (2018)
- [Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps](https://mlsanity.com/paper/2207.03380/) (2022)
- [Language models are better than humans at next-token prediction](https://mlsanity.com/paper/2212.11281/) (2022)
- [Duality of Bures and Shape Distances with Implications for Comparing Neural Representations](https://mlsanity.com/paper/2311.11436/) (2023)
- [Inductive biases, pretraining and fine-tuning jointly account for brain responses to speech](https://mlsanity.com/paper/2103.01032/) (2021)
- [Brain-Model Evaluations Need the NeuroAI Turing Test](https://mlsanity.com/paper/2502.16238/) (2025)
- [TopoLM: brain-like spatio-functional organization in a topographic language model](https://mlsanity.com/paper/2410.11516/) (2024)
- [Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures](https://mlsanity.com/paper/2311.04547/) (2023)
- [What Are Large Language Models Mapping to in the Brain? A Case Against Over-Reliance on Brain Scores](https://mlsanity.com/paper/2406.01538/) (2024)

## Built on by (most cited first, 30 of 30)

- [Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization](https://mlsanity.com/paper/2506.13331/) (2025)
- [How Syntax Specialization Emerges in Language Models](https://mlsanity.com/paper/2505.19548/) (2025)
- [fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI Understanding](https://mlsanity.com/paper/2511.21760/) (2025)
- [Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining](https://mlsanity.com/paper/2509.05291/) (2025)
- [Linguistics and Human Brain: A Perspective of Computational Neuroscience](https://mlsanity.com/paper/2602.08275/) (2026)
- [Beyond representational alignment with brain-guided language models for robust reasoning](https://mlsanity.com/paper/2606.11893/) (2026)
- [Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment](https://mlsanity.com/paper/2503.19586/) (2025)
- [LITcoder: A General-Purpose Library for Building and Comparing Encoding Models](https://mlsanity.com/paper/2509.09152/) (2025)
- [Fine-grained Analysis of Brain-LLM Alignment through Input Attribution](https://mlsanity.com/paper/2510.12355/) (2025)
- [Abstraction Induces the Brain Alignment of Language and Speech Models](https://mlsanity.com/paper/2602.04081/) (2026)
- [Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model](https://mlsanity.com/paper/2606.09770/) (2026)
- [Vectors from Larger Language Models Predict Human Reading Time and fMRI Data More Poorly when Dimensionality Expansion is Controlled](https://mlsanity.com/paper/2505.12196/) (2025)
- [Neural Correlates of Language Models Are Specific to Human Language](https://mlsanity.com/paper/2510.03156/) (2025)
- [The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models](https://mlsanity.com/paper/2601.19926/) (2026)
- [Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents](https://mlsanity.com/paper/2603.27626/) (2026)
- [MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding](https://mlsanity.com/paper/2605.29850/) (2026)
- [Interpreting Brain Responses to Language with Sparse Features from Language Models](https://mlsanity.com/paper/2606.06857/) (2026)
- [NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity](https://mlsanity.com/paper/2607.02317/) (2026)
- [Better audio representations are more brain-like: linking model-brain alignment with performance in downstream auditory tasks](https://mlsanity.com/paper/2511.16849/) (2025)
- [What does it mean to understand language?](https://mlsanity.com/paper/2511.19757/) (2025)
- [Training-Driven Representational Geometry Modularization Predicts Brain Alignment in Language Models](https://mlsanity.com/paper/2602.07539/) (2026)
- [Linguistic properties and model scale in brain encoding: from small to compressed language models](https://mlsanity.com/paper/2602.07547/) (2026)
- [Left-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence](https://mlsanity.com/paper/2602.12811/) (2026)
- [Traces of Social Competence in Large Language Models](https://mlsanity.com/paper/2603.04161/) (2026)
- [Large Language Models Align with the Human Brain during Creative Thinking](https://mlsanity.com/paper/2604.03480/) (2026)
- [Independent-Component-Based Encoding Models of Brain Activity During Story Comprehension](https://mlsanity.com/paper/2604.24942/) (2026)
- [Brain-LLM Alignment Tracks Training Data, Not Typology](https://mlsanity.com/paper/2605.23032/) (2026)
- [Do VLMs Align Better with Humans than LLMs during Natural Reading?](https://mlsanity.com/paper/2605.28818/) (2026)
- [Reward Valuation in Large Language Models: Causal Induction of Anhedonia](https://mlsanity.com/paper/2607.06626/) (2026)
- [Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and Cognition](https://mlsanity.com/paper/2609.07474/) (2026)

## Abstract (arXiv)

Large language models (LLMs) exhibit remarkable similarity to neural activity in the human language network. However, the key properties of language shaping brain-like representations, and their evolution during training as a function of different tasks remain unclear. We here benchmark 34 training checkpoints spanning 300B tokens across 8 different model sizes to analyze how brain alignment relates to linguistic competence. Specifically, we find that brain alignment tracks the development of formal linguistic competence -- i.e., knowledge of linguistic rules -- more closely than functional linguistic competence. While functional competence, which involves world knowledge and reasoning, continues to develop throughout training, its relationship with brain alignment is weaker, suggesting that the human language network primarily encodes formal linguistic structure rather than broader cognitive functions. We further show that model size is not a reliable predictor of brain alignment when controlling for feature size and find that the correlation between next-word prediction, behavioral alignment and brain alignment fades once models surpass human language proficiency. Finally, using the largest set of rigorous neural language benchmarks to date, we show that language brain alignment benchmarks remain unsaturated, highlighting opportunities for improving future models. Taken together, our findings suggest that the human language network is best modeled by formal, rather than functional, aspects of language.