# The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer

arXiv: https://arxiv.org/abs/2610.03827 · HTML: https://mlsanity.com/paper/2610.03827/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 12 of 12)

- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Choosing Transfer Languages for Cross-Lingual Learning](https://mlsanity.com/paper/1905.12688/) (2019)
- [MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2504.02768/) (2025)
- [Cross-Linguistic Syntactic Evaluation of Word Prediction Models](https://mlsanity.com/paper/2005.00187/) (2020)
- [Injecting structural hints: Using language models to study inductive biases in language learning](https://mlsanity.com/paper/2304.13060/) (2023)
- [Learning Inductive Biases with Simple Neural Networks](https://mlsanity.com/paper/1802.02745/) (2018)
- [Linguistics and Human Brain: A Perspective of Computational Neuroscience](https://mlsanity.com/paper/2602.08275/) (2026)
- [Inductive Biases for Zero-shot Systematic Generalization in Language-informed Reinforcement Learning](https://mlsanity.com/paper/2501.15270/) (2025)

## Abstract (arXiv)

Similarity scores are often offered as evidence that a model shares structure with the brain or across languages. We ask what such a score reads when that structure is removed, or when the instrument measuring it does not work, in two settings. Across seventeen languages, a grammaticality probe transfers worse between more distant languages (r = -0.66). But the probe's own accuracy falls along the same axis and is at chance in four languages, four of the five most distant. Dropping them halves the explained variance, and because it also narrows the range of distances, the design cannot say how much of the gradient is the instrument. Counting the 272 language pairs as independent gives p = 0.0006 for a steering effect that is null when the seventeen languages are the unit (p = 0.155). In brain alignment, a training objective raises a language model's similarity to fMRI responses from 0.10 to 0.34 (reliability ceiling 0.54), yet targets with the brain correspondence destroyed still reach 0.31. A shuffled target scores about k/n against the real one, for rank k and n sentences, a baseline that can be computed before any model is trained. Both interventions work, yet we detect no distance-graded steering effect and no syntactic benefit from alignment. Before reading a correspondence score, measure how much of it survives without the correspondence.