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

arXiv: https://arxiv.org/abs/2603.23091 · HTML: https://mlsanity.com/paper/2603.23091/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 7 of its 50 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [Disentangling Syntax and Semantics in the Brain with Deep Networks](https://mlsanity.com/paper/2103.01620/) (2021)
- [Does injecting linguistic structure into language models lead to better alignment with brain recordings?](https://mlsanity.com/paper/2101.12608/) (2021)
- [NeuroAI for AI Safety](https://mlsanity.com/paper/2411.18526/) (2024)
- [BrainWavLM: Fine-tuning Speech Representations with Brain Responses to Language](https://mlsanity.com/paper/2502.08866/) (2025)

## Built on by (most cited first, 2 of 2)

- [The Platonic brain bridge hypothesis: human brain networks as an architectural prior for multimodal large language models](https://mlsanity.com/paper/2609.10947/) (2026)
- [Which Attention Heads are like the Human Head? Not the Ones that Compute](https://mlsanity.com/paper/2609.37991/) (2026)

## Abstract (arXiv)

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.