ArticleNature communications2024
Shared functional specialization in transformer-based language models and the human brain.
Article in Nature communications, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 26 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
26 citing papers in PubMed.
- Review
- A population code for semantics in human hippocampus.Nature neuroscience · 2026Article
- Article
- Article
- Brain-AI convergence: Generative world models and hierarchical attention for human intelligence.Patterns (New York, N.Y.) · 2026Review
- Review
- Evidence Against Syntactic Encapsulation in Large Language Models.Cognitive science · 2026Article
- Article
- A deep neural network model of audiovisual speech recognition reports the McGurk effect.Psychonomic bulletin & review · 2026Article
- Aligning brains into a shared space improves their alignment with large language models.Nature computational science · 2026Article
- Disentangling Superpositions: Interpretable Brain Encoding Model with Sparse Concept Atoms.bioRxiv : the preprint server for biology · 2026Article
- Advances in LLM Reasoning Enable Flexibility in Clinical Problem-Solving.AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science · 2026Article
- Characterization of the spatiotemporal representations of visual, semantic, and memorability features in the human brain.PLoS biology · 2026Article
- A Deep Neural Network Model of Audiovisual Speech Recognition Reports the McGurk Effect.bioRxiv : the preprint server for biology · 2025Article
- Contextual assembly of lexical functions in large language models.Behavior research methods · 2025Article
- Limitations of large language models in clinical problem-solving arising from inflexible reasoning.Scientific reports · 2025Article
- Increasing alignment of large language models with language processing in the human brain.Nature computational science · 2025Article
- Emergence of a temporal processing gradient from naturalistic inputs and network connectivity.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- Linguistic coupling between neural systems for speech production and comprehension during real-time dyadic conversations.bioRxiv : the preprint server for biology · 2025Article
- Big data approaches for novel mechanistic insights on sleep and circadian rhythms: a workshop summary.Sleep · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
9 authors.
Funding
Abstract
When processing language, the brain is thought to deploy specialized computations to construct meaning from complex linguistic structures. Recently, artificial neural networks based on the Transformer architecture have revolutionized the field of natural language processing. Transformers integrate contextual information across words via structured circuit computations. Prior work has focused on the internal representations ("embeddings") generated by these circuits. In this paper, we instead analyze the circuit computations directly: we deconstruct these computations into the functionally-specialized "transformations" that integrate contextual information across words. Using functional MRI data acquired while participants listened to naturalistic stories, we first verify that the transformations account for considerable variance in brain activity across the cortical language network. We then demonstrate that the emergent computations performed by individual, functionally-specialized "attention heads" differentially predict brain activity in specific cortical regions. These heads fall along gradients corresponding to different layers and context lengths in a low-dimensional cortical space.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.