mlsanityData to 7 Oct 2026

Joint processing of linguistic properties in brains and language models

arXiv 2212.08094 ↗First posted 15 Dec 2022cs.CL q-bio.NCcited by 37

Not on the map. Why?

Abstract (arXiv)

Language models have been shown to be very effective in predicting brain recordings of subjects experiencing complex language stimuli. For a deeper understanding of this alignment, it is important to understand the correspondence between the detailed processing of linguistic information by the human brain versus language models. We investigate this correspondence via a direct approach, in which we eliminate information related to specific linguistic properties in the language model representations and observe how this intervention affects the alignment with fMRI brain recordings obtained while participants listened to a story. We investigate a range of linguistic properties (surface, syntactic, and semantic) and find that the elimination of each one results in a significant decrease in brain alignment. Specifically, we find that syntactic properties (i.e. Top Constituents and Tree Depth) have the largest effect on the trend of brain alignment across model layers. These findings provide clear evidence for the role of specific linguistic information in the alignment between brain and language models, and open new avenues for mapping the joint information processing in both systems. We make the code publicly available [https://github.com/subbareddy248/linguistic-properties-brain-alignment].

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 15 of its 61 references that are in the map. First posted on arXiv 15 Dec 2022.

Builds on

15 of 61 references.

References · 15

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020A Primer in BERTology: What we know about how BERT workscited by 807
  3. 2018What you can cram into a single vector: Probing sentence embeddings for linguistic propertiescited by 452
  4. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  5. 2016Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Taskscited by 216
  6. 2019Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)cited by 128
  7. 2019Linguistic generalization and compositionality in modern artificial neural networkscited by 58
  8. 2019Inducing brain-relevant bias in natural language processing modelscited by 38
  9. 2019Linking artificial and human neural representations of languagecited by 37
  10. 2021Exploring the Role of BERT Token Representations to Explain Sentence Probing Resultscited by 29
  11. 2019CogniVal: A Framework for Cognitive Word Embedding Evaluationcited by 27
  12. 2022Neural Language Taskonomy: Which NLP Tasks are the most Predictive of fMRI Brain Activity?cited by 27
3 more
  1. 2022Language models and brains align due to more than next-word prediction and word-level informationcited by 14
  2. 2019Relating Simple Sentence Representations in Deep Neural Networks and the Braincited by 10
  3. 2021Analysis and Prediction of NLP Models Via Task Embeddingscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 8; 2025: 12; 2026: 7.

37 papers.

Sort:

By area:

  1. 2023Getting aligned on representational alignmentcited by 142
  2. 2023Scaling laws for language encoding models in fMRIcited by 68
  3. 2023Explaining black box text modules in natural language with language modelscited by 61
  4. 2023Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)cited by 20
  5. 2024Improving Semantic Understanding in Speech Language Models via Brain-tuningcited by 20
  6. 2023Speech language models lack important brain-relevant semanticscited by 19
  7. 2025Vision Function Layer in Multimodal LLMscited by 17
  8. 2023ROSE: A Neurocomputational Architecture for Syntaxcited by 15
  9. 2024Evidence from fMRI Supports a Two-Phase Abstraction Process in Language Modelscited by 13
  10. 2024Crafting Interpretable Embeddings by Asking LLMs Questionscited by 11
  11. 2023Mapping Brains with Language Models: A Surveycited by 8
  12. 2025Multi-modal brain encoding models for multi-modal stimulicited by 8
25 more
  1. 2025Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learningcited by 7
  2. 2024Generative causal testing to bridge data-driven models and scientific theories in language neurosciencecited by 5
  3. 2024Computational Models to Study Language Processing in the Human Brain: A Surveycited by 4
  4. 2025Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspectivecited by 4
  5. 2025Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)cited by 4
  6. 2025Language models align with brain regions that represent concepts across modalitiescited by 4
  7. 2025Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantagecited by 4
  8. 2025Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglementcited by 4
  9. 2023Divergences between Language Models and Human Brainscited by 3
  10. 2024Metric Learning Encoding Models: A Multivariate Framework for Interpreting Neural Representationscited by 3
  11. 2024Brain-like Functional Organization within Large Language Modelscited by 3
  12. 2025Fine-grained Analysis of Brain-LLM Alignment through Input Attributioncited by 3
  13. 2024Interpretable Next-token Prediction via the Generalized Induction Headcited by 2
  14. 2025LITcoder: A General-Purpose Library for Building and Comparing Encoding Modelscited by 2
  15. 2025Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Braincited by 2
  16. 2026Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networkscited by 2
  17. 2026Abstraction Induces the Brain Alignment of Language and Speech Modelscited by 2
  18. 2026Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topographycited by 2
  19. 2023Syntactic Structure Processing in the Brain while Listeningcited by 1
  20. 2023Attention, not scale, drives human-AI alignment in multimodal language predictioncited by 1
  21. 2025Probing Multimodal Fusion in the Brain: The Dominance of Audiovisual Streams in Naturalistic Encodingcited by 1
  22. 2026Linguistic properties and model scale in brain encoding: from small to compressed language modelscited by 0
  23. 2026Large Language Models Align with the Human Brain during Creative Thinkingcited by 0
  24. 2026Independent-Component-Based Encoding Models of Brain Activity During Story Comprehensioncited by 0
  25. 2026Do speech foundation models really learn words?cited by 0