The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Model Collapse Demystified: The Case of Regression
Open accessAbstract
In the era of proliferation of large language and image generation models, the phenomenon of "model collapse" refers to the situation whereby as a model is trained recursively on data generated from previous generations of itself over time, its performance degrades until the model eventually becomes completely useless, i.e the model collapses. In this work, we study this phenomenon in the setting of high-dimensional regression and obtain analytic formulae which quantitatively outline this phenomenon in a broad range of regimes. In the special case of polynomial decaying spectral and source conditions, we obtain modified scaling laws which exhibit new crossover phenomena from fast to slow rates. We also propose a simple strategy based on adaptive regularization to mitigate model collapse. Our theoretical results are validated with experiments.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“As successive generations of models are trained on data increasingly contaminated by historical synthetic outputs, the system progressively erodes distributional diversity and collapses functional modes—a degenerative process that remains robust to scale and is highly sensitive to even minimal synthetic fractions [14,15].”
From Self-Referential Introspection in Large Language Models: The Critical Threshold for Recursive Self-Improvement (2026) · cites this paper as [15]
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
Narrative Creativity: An Introduction to How and Why
Fletcher, A., & Benveniste, M. (2025) · Cambridge University Press eBooks · doi:10.1017/9781009614801 · Cited by 17
A Guide to Machine Learning Epistemic Ignorance, Hidden Paradoxes, and Other Tensions
Naser, M. Z. (2025) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70038 · Cited by 17
Zhang, J., Yuan, B., & Zhang, Q. (2026) · Entropy · doi:10.3390/e28090951 · Cited by 2
Lost in Retraining: Closed-Loop Learning and Model Collapse in Exponential Families
Jangjoo, F., di Sarra, G., Marsili, M., & Roudi, Y. (2026) · Physical Review Letters · doi:10.1103/156q-3ngc · Cited by 2
Motamarri, S. S., Chaitanya, N., Krishnan, G., & Agarwal, P. R. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-12830-0_24
Metadata
- Authors
- Dohmatob, E., Feng, Y., & Kempe, J.
- ORCID
- Kempe, Julia
- Venue
- Advances in Neural Information Processing Systems 37
- Published
- 2024
- Pages
- 46979-47013
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W4415797795
- Cited by
- 10
- References
- 0
- Citations by year
- 2026: 7 · 2025: 2 · 2024: 1
- FWCI
- 15.04
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Statistical Methods and Models
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
- Keywords
- model collapse, regression analysis, overfitting, neural network training, gradient vanishing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Model Collapse Demystified: The Case of Regression. https://app.cochat.ai/papers/10.52202/079017-1490
- The paper
- Dohmatob, E., Feng, Y., & Kempe, J. (2024). Model Collapse Demystified: The Case of Regression. Advances in Neural Information Processing Systems 37. https://doi.org/10.52202/079017-1490
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.