研究：自然语言训练而非代码抽象塑造更接近大脑的表示几何

View PDF HTML (experimental)

Abstract:Code-trained language models produce positive brain scores, which raises the question of whether abstract structure learned from programming languages can substitute for natural-language training. We trained 25 GPT-2-small models on TinyStories, Python, C functions, x86-64 assembly, and the corresponding machine code, and scored them using a shared tokenizer and encoding procedure against matched random-weight models. On Pereira-243 and Tuckute2024, TinyStories exceeds the mean of the four code models by $\Delta r = 0.053$ and $0.059$ (Holm-corrected $p<0.001$), while code training leaves alignment near the random-weight level. The language advantage is benchmark-specific: Blank2014 shows no corrected language-code difference, and Fedorenko2016 shows no language benefit. Geometry tracks the encoding result on Pereira-243: TinyStories seeds converge on the most similar representations, and its fit-free correspondence with neural dissimilarity peaks at $\rho = 0.14$, twice the code and random-weight levels. Binary-trained models have about three effective dimensions, so seed agreement alone does not imply neural correspondence. Updating only the embedding matrix on English improves mean-over-depth alignment for every code model more than an equal update on its own corpus. Within this architecture and training setup, natural-language training produces a distinct representational geometry with closer neural correspondence on Pereira-243

Comments:	Accepted for the Neureps Workshop at NeurIPS 2026
Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2611.09027 [cs.CL]
	(or arXiv:2611.09027v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2611.09027 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Iñigo Parra [view email]
[v1] Fri, 6 Nov 2026 06:02:06 UTC (302 KB)