Developmental approach reveals the statistical learning of Neural Language Models: Transformers generalize from the most abstract statistical patterns
This study uses a developmental approach to investigate the statistical learning and mental representation of neural language models (NLM). A series of Generative Transformer models are trained on a synthetic grammar, and model states are saved at multiple stages. By analyzing changes in internal representations, the authors find that NLMs acquire the most abstract global statistical knowledge at the beginning of learning, and later acquire local statistical dependencies. This learning path contains many over-generalizations from the start, which are gradually constrained later. Based on this observation, a new framework is proposed to explain the statistical learning and language cognition of NLMs.
[2606.27460] Developmental approach reveals the statistical learning of Neural Language Models: Transformers generalize from the most abstract statistical patterns
[Submitted on 25 Jun 2026]
Title:Developmental approach reveals the statistical learning of Neural Language Models: Transformers generalize from the most abstract statistical patterns
View a PDF of the paper titled Developmental approach reveals the statistical learning of Neural Language Models: Transformers generalize from the most abstract statistical patterns, by Wang Bojun and 2 other authors
View PDF HTML (experimental)
Abstract:In this study, we use a developmental approach to investigate the statistical learning and mental representation of neural language models (NLM). A series of Generative Transformer models are trained on a synthetic grammar. The model states are saved at multiple stages in the course of training. Through analyzing how the internal representations of these models change in the developmental path, we found that NLMs acquire the most abstract global statistical knowledge at the beginning of learning and later acquire the relatively local statistical dependencies. This learning path contains many over-generalizations from the very beginning and these over-generalizations are gradually constrained in the later stage of learning. Based on this observation, we propose a new framework to explain the statistical learning and language cognition of NLMs.
Comments: 10 pages, 7 figures, oral presentation at Interdisciplinary Advances in Statistical Learning
Subjects:
Computation and Language (cs.CL)
Cite as: arXiv:2606.27460 [cs.CL]
(or arXiv:2606.27460v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.27460
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Bojun Wang [view email] [v1] Thu, 25 Jun 2026 18:34:56 UTC (1,124 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Developmental approach reveals the statistical learning of Neural Language Models: Transformers generalize from the most abstract statistical patterns, by Wang Bojun and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)