Pith. sign in

REVIEW 3 cited by

A Probabilistic Perspective on Model Collapse

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.13947 v2 pith:QVADTLOF submitted 2025-05-20 stat.ML cs.LG

A Probabilistic Perspective on Model Collapse

classification stat.ML cs.LG
keywords modeltrainingcollapseestimationprobabilisticrecursivesizebias
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In recent years, model collapse has become a critical issue in language model training, making it essential to understand the underlying mechanisms driving this phenomenon. In this paper, we investigate recursive parametric model training from a probabilistic perspective, aiming to characterize the conditions under which model collapse occurs and, crucially, how it can be mitigated. We conceptualize the recursive training process as a random walk of the model estimate, highlighting how the sample size influences the step size and how the estimation procedure determines the direction and potential bias of the random walk. Under mild conditions, we rigorously show that progressively increasing the sample size at each training step is necessary to prevent model collapse. In particular, when the estimation is unbiased, the required growth rate follows a superlinear pattern. This rate needs to be accelerated even further in the presence of substantial estimation bias. Building on this probabilistic framework, we also investigate the probability that recursive training on synthetic data yields models that outperform those trained solely on real data. Moreover, we extend these results to general parametric model family in an asymptotic regime. Finally, we validate our theoretical results through extensive simulations and a real-world dataset.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences

    cs.LG 2026-05 unverdicted novelty 7.0

    Recursive generative retraining with pluralistic preferences converges to a stable diverse distribution that satisfies a weighted Nash bargaining solution.

  2. Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences

    cs.LG 2026-05 unverdicted novelty 6.0

    Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.

  3. Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence

    stat.ML 2025-10 conditional novelty 6.0

    Verifier-filtered synthetic retraining improves linear-regression estimates in the short term but converges to the verifier's knowledge center, so sustained improvement requires an unbiased verifier.