mlsanityData to 7 Oct 2026

Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage

arXiv 2510.17833 ↗First posted 3 Oct 2025q-bio.NC cs.AIcited by 4

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

Do brains and language models converge toward the same internal representations of the world? Recent years have seen a rise in studies of neural activations and model alignment. In this work, we review 25 fMRI-based studies published between 2023 and 2025 and explicitly confront their findings with two key hypotheses: (i) the Platonic Representation Hypothesis -- that as models scale and improve, they converge to a representation of the real world, and (ii) the Intermediate-Layer Advantage -- that intermediate (mid-depth) layers often encode richer, more generalizable features. Our findings provide converging evidence that models and brains may share abstract representational structures, supporting both hypotheses and motivating further research on brain-model alignment.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 69 of its 104 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

69 of 104 references.

References · 69

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  7. 2024The Llama 3 Herd of Modelscited by 14,192
  8. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  9. 2023Visual Instruction Tuningcited by 7,792
  10. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  11. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  12. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
38 more
  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  6. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  7. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  8. 2020Longformer: The Long-Document Transformercited by 3,362
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  10. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  11. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  12. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  13. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  14. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  15. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  16. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  17. 2021ViViT: A Video Vision Transformercited by 1,610
  18. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  19. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
  20. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  21. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,096
  22. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  23. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  24. 2021FLAVA: A Foundational Language And Vision Alignment Modelcited by 646
  25. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  26. 2022GIT: A Generative Image-to-text Transformer for Vision and Languagecited by 536
  27. 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documentscited by 316
  28. 2025Layer by Layer: Uncovering Hidden Representations in Language Modelscited by 293
  29. 2021BookSum: A Collection of Datasets for Long-form Narrative Summarizationcited by 184
  30. 2019Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)cited by 128
  31. 2024Scalable Pre-training of Large Autoregressive Image Modelscited by 115
  32. 2023Scaling laws for language encoding models in fMRIcited by 68
  33. 2022BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learningcited by 56
  34. 2023Instruction-tuning Aligns LLMs to the Human Braincited by 39
  35. 2022Joint processing of linguistic properties in brains and language modelscited by 37
  36. 2023The Algonauts Project 2023 Challenge: How the Human Brain Makes Sense of Natural Scenescited by 34
  37. 2023Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural languagecited by 32
  38. 2023Brain encoding models based on multimodal transformers can transfer across language and visioncited by 31

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Linguistics and Human Brain: A Perspective of Computational Neurosciencecited by 3
  2. 2026Toward Aristotelian Medical Representations: Backpropagation-Free Layer-wise Analysis for Interpretable Generalized Metric Learning on MedMNISTcited by 2
  3. 2026Do VLMs Align Better with Humans than LLMs during Natural Reading?cited by 0
  4. 2026The Platonic brain bridge hypothesis: human brain networks as an architectural prior for multimodal large language modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Cross-lingual brain-language model alignment is robust but challenges hierarchical and computational accounts
  2. 2026Linguistic properties and model scale in brain encoding: from small to compressed language models
  3. 2026Abstraction Induces the Brain Alignment of Language and Speech Models
  4. 2026Cognitive Expert Language Models Better Align with the Corresponding Brain Systems
  5. 2026Do Language Models Align with Brains? Prediction Scores Are Not Enough
  6. 2026Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment
  7. 2026Brain-LLM Alignment Tracks Training Data, Not Typology
  8. 2024Vision-Language Models Align with Human Neural Representations in Concept Processing