When Language Models Lose Their Mind: The Consequences of Brain Misalignment

• URL: http://arxiv.org/abs/2603.23091v1
• Date: Tue, 24 Mar 2026 11:39:54 GMT
• Title: When Language Models Lose Their Mind: The Consequences of Brain Misalignment
• Abstract summary: We introduce brain-misaligned large language models (LLMs) and train them to predict brain activity poorly.<n>We evaluate these models on over 200 downstream tasks encompassing diverse linguistic domains, including semantics, syntax, discourse, reasoning, and morphology.<n>Our experiments reveal that brain misalignment substantially impairs downstream performance, highlighting the critical role of brain alignment in achieving robust linguistic competence.
• Score: 8.694405135908484
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While brain-aligned large language models (LLMs) have garnered attention for their potential as cognitive models and for potential for enhanced safety and trustworthiness in AI, the role of this brain alignment for linguistic competence remains uncertain. In this work, we investigate the functional implications of brain alignment by introducing brain-misaligned models--LLMs intentionally trained to predict brain activity poorly while maintaining high language modeling performance. We evaluate these models on over 200 downstream tasks encompassing diverse linguistic domains, including semantics, syntax, discourse, reasoning, and morphology. By comparing brain-misaligned models with well-matched brain-aligned counterparts, we isolate the specific impact of brain alignment on language understanding. Our experiments reveal that brain misalignment substantially impairs downstream performance, highlighting the critical role of brain alignment in achieving robust linguistic competence. These findings underscore the importance of brain alignment in LLMs and offer novel insights into the relationship between neural representations and linguistic processing.

Related papers

• BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language [65.1211456110319]
  BrainJanus is the first unified brain model that integrates brain, vision, and language within a single framework.<n>Our framework exhibits zero-shot generalization preserves and interpretable biological topography, highlighting its potential as a general-purpose brain modeling paradigm.
  arXiv  Detail & Related papers  (2026-06-29T14:02:15Z)
• Linguistic properties and model scale in brain encoding: from small to compressed language models [39.040386424307165]
  Recent work has shown that scaling large language models (LLMs) improves their alignment with human brain activity.<n>This raises a fundamental question: what is the minimal model capacity required to capture brain-relevant representations?<n>We investigate how constraining model scale and numerical precision affects brain alignment.
  arXiv  Detail & Related papers  (2026-02-07T13:48:45Z)
• Language models align with brain regions that represent concepts across modalities [41.64161126642105]
  We investigate the relationship between language models (LMs) and two neural metrics.<n>Our experiments show that both language-only and language-vision models predict the signal better in more meaning-consistent areas of the brain.
  arXiv  Detail & Related papers  (2025-08-15T15:32:19Z)
• From Language to Cognition: How LLMs Outgrow the Human Language Network [21.08557980312889]
  Large language models (LLMs) exhibit remarkable similarity to neural activity in the human language network.<n>We benchmark 34 training checkpoints spanning 300B tokens across 8 different model sizes to analyze how brain alignment relates to linguistic competence.
  arXiv  Detail & Related papers  (2025-03-03T18:54:19Z)
• MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data [64.92867794764247]
  MindAligner is a framework for cross-subject brain decoding from limited fMRI data.<n>Brain Transfer Matrix (BTM) projects the brain signals of an arbitrary new subject to one of the known subjects.<n>Brain Functional Alignment module is proposed to perform soft cross-subject brain alignment under different visual stimuli.
  arXiv  Detail & Related papers  (2025-02-07T16:01:59Z)
• Brain-like Functional Organization within Large Language Models [58.93629121400745]
  The human brain has long inspired the pursuit of artificial intelligence (AI) Recent neuroimaging studies provide compelling evidence of alignment between the computational representation of artificial neural networks (ANNs) and the neural responses of the human brain to stimuli. In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs) This framework links the AN sub-groups to FBNs, enabling the delineation of brain-like functional organization within large language models (LLMs)
  arXiv  Detail & Related papers  (2024-10-25T13:15:17Z)
• Large Language Model-based FMRI Encoding of Language Functions for Subjects with Neurocognitive Disorder [53.575426835313536]
  This paper explores language-related functional changes in older NCD adults using LLM-based fMRI encoding and brain scores. We analyze the correlation between brain scores and cognitive scores at both whole-brain and language-related ROI levels. Our findings reveal that higher cognitive abilities correspond to better brain scores, with correlations peaking in the middle temporal gyrus.
  arXiv  Detail & Related papers  (2024-07-15T01:09:08Z)
• Lost in Translation: The Algorithmic Gap Between LMs and the Brain [8.799971499357499]
  Language Models (LMs) have achieved impressive performance on various linguistic tasks, but their relationship to human language processing in the brain remains unclear. This paper examines the gaps and overlaps between LMs and the brain at different levels of analysis. We discuss how insights from neuroscience, such as sparsity, modularity, internal states, and interactive learning, can inform the development of more biologically plausible language models.
  arXiv  Detail & Related papers  (2024-07-05T17:43:16Z)
• Joint processing of linguistic properties in brains and language models [14.997785690790032]
  We investigate the correspondence between the detailed processing of linguistic information by the human brain versus language models. We find that elimination of specific linguistic properties results in a significant decrease in brain alignment. These findings provide clear evidence for the role of specific linguistic information in the alignment between brain and language models.
  arXiv  Detail & Related papers  (2022-12-15T19:13:42Z)
• Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps [75.84770193489639]
  We examine the impact of test loss, training corpus and model architecture on the prediction of functional Magnetic Resonance Imaging timecourses of participants listening to an audiobook. We find that untrained versions of each model already explain significant amount of signal in the brain by capturing similarity in brain responses across identical words. We suggest good practices for future studies aiming at explaining the human language system using neural language models.
  arXiv  Detail & Related papers  (2022-07-07T15:37:17Z)
• Model-based analysis of brain activity reveals the hierarchy of language in 305 subjects [82.81964713263483]
  A popular approach to decompose the neural bases of language consists in correlating, across individuals, the brain responses to different stimuli. Here, we show that a model-based approach can reach equivalent results within subjects exposed to natural stimuli.
  arXiv  Detail & Related papers  (2021-10-12T15:30:21Z)
• Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses [62.197912623223964]
  We show a low-dimensional structure where language models and translation models smoothly interpolate between word embeddings, syntactic and semantic tasks, and future word embeddings. We find that this representation embedding can predict how well each individual feature space maps to human brain responses to natural language stimuli recorded using fMRI. This suggests that the embedding captures some part of the brain's natural language representation structure.
  arXiv  Detail & Related papers  (2021-06-09T22:59:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.