# What Are Large Language Models Mapping to in the Brain? A Case Against Over-Reliance on Brain Scores

arXiv: https://arxiv.org/abs/2406.01538 · HTML: https://mlsanity.com/paper/2406.01538/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 45 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Builds on (most cited first, 10 of 10)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)](https://mlsanity.com/paper/1905.11833/) (2019)
- [Scaling laws for language encoding models in fMRI](https://mlsanity.com/paper/2305.11863/) (2023)
- [The Natural Stories Corpus](https://mlsanity.com/paper/1708.05763/) (2017)
- [Disentangling Syntax and Semantics in the Brain with Deep Networks](https://mlsanity.com/paper/2103.01620/) (2021)
- [Neural Language Taskonomy: Which NLP Tasks are the most Predictive of fMRI Brain Activity?](https://mlsanity.com/paper/2205.01404/) (2022)
- [Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps](https://mlsanity.com/paper/2207.03380/) (2022)
- [Training language models to summarize narratives improves brain alignment](https://mlsanity.com/paper/2212.10898/) (2022)
- [LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond](https://mlsanity.com/paper/2105.12449/) (2021)
- [The out-of-sample R2: estimation and inference](https://mlsanity.com/paper/2302.05131/) (2023)

## Built on by (most cited first, 10 of 10)

- [From Language to Cognition: How LLMs Outgrow the Human Language Network](https://mlsanity.com/paper/2503.01830/) (2025)
- [Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network](https://mlsanity.com/paper/2406.15109/) (2024)
- [Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning](https://mlsanity.com/paper/2508.10057/) (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)
- [Brain-like emergent properties in deep networks: impact of network architecture, datasets and training](https://mlsanity.com/paper/2411.16326/) (2024)
- [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)
- [Surprisal from Larger Transformer-based Language Models Predicts fMRI Data More Poorly](https://mlsanity.com/paper/2506.11338/) (2025)
- [Neural Correlates of Language Models Are Specific to Human Language](https://mlsanity.com/paper/2510.03156/) (2025)
- [Brain Score Tracks Shared Properties of Languages: Evidence from Many Natural Languages and Structured Sequences](https://mlsanity.com/paper/2604.15503/) (2026)
- [Large Language Models as Modal Models in Linguistics](https://mlsanity.com/paper/2606.10467/) (2026)

## Abstract (arXiv)

Given the remarkable capabilities of large language models (LLMs), there has been a growing interest in evaluating their similarity to the human brain. One approach towards quantifying this similarity is by measuring how well a model predicts neural signals, also called "brain score". Internal representations from LLMs achieve state-of-the-art brain scores, leading to speculation that they share computational principles with human language processing. This inference is only valid if the subset of neural activity predicted by LLMs reflects core elements of language processing. Here, we question this assumption by analyzing three neural datasets used in an impactful study on LLM-to-brain mappings, with a particular focus on an fMRI dataset where participants read short passages. We first find that when using shuffled train-test splits, as done in previous studies with these datasets, a trivial feature that encodes temporal autocorrelation not only outperforms LLMs but also accounts for the majority of neural variance that LLMs explain. We therefore use contiguous splits moving forward. Second, we explain the surprisingly high brain scores of untrained LLMs by showing they do not account for additional neural variance beyond two simple features: sentence length and sentence position. This undermines evidence used to claim that the transformer architecture biases computations to be more brain-like. Third, we find that brain scores of trained LLMs on this dataset can largely be explained by sentence length, position, and pronoun-dereferenced static word embeddings; a small, additional amount is explained by sense-specific embeddings and contextual representations of sentence structure. We conclude that over-reliance on brain scores can lead to over-interpretations of similarity between LLMs and brains, and emphasize the importance of deconstructing what LLMs are mapping to in neural signals.