arXiv Machine Learning
Who Pays for the Knowledge Models Copy? Model Collapse as Rogers' Paradox
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jul 7
Language Generation with Replay: A Learning-Theoretic View of Model Collapse
arXiv:2603. 11784v2 Announce Type: replace Abstract: As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed.
arXiv Machine Learning
Sep 11
A Fragility Spectrum for Recursive Language-Model Training
The paper investigates how recursive contamination—retraining language models on their own generated text—affects output diversity across 13 publicly released checkpoints. Using a fixed contamination protocol over five generations, the authors find a wide spread in 4‑gram diversity (0.187 to 0.940), indicating that some models collapse into repetitive fragments while others remain largely unaffected. The study shows that a model’s susceptibility to collapse is an intrinsic property of the checkpoint, not predicted by parameter scale or static indicators, and that simple interventions such as tightening top‑p sampling can significantly slow or halt collapse.
arXiv Machine Learning
Jul 14
Can a Language Model Learn Facts Continually in Its Weights?
arXiv:2607. 11020v1 Announce Type: cross Abstract: Continual learning promises a language model that keeps acquiring knowledge after training, with each new fact written into its weights.
arXiv Machine Learning
Oct 8
When Should an In-Context Learner Expand Its Hypothesis Space?
The paper investigates when an in‑context learner should expand its hypothesis space, framing the decision as a costly sequential problem where prediction failures must be translated into structural evidence and then into an action. Using a Structural Revision Environment that allows exact Bayesian analysis, the authors find that the optimal decision to expand is governed by a value boundary rather than a simple evidence threshold, and that this boundary depends on the price of expansion, the remaining horizon, and the specific predictions that cannot be repaired locally. Experiments with transformers and language models show that while these models exhibit a failure‑sensitive signal, they often fail to incorporate cost and horizon considerations into their expansion decisions, and post‑training adjustments to priors or prediction sharpness do not alter the expansion criterion.
arXiv Computation and Language
Sep 22
Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting
The paper investigates time‑incremental continued pretraining (CPT) of large language models using web‑scale data that overlaps across snapshots. Across six open‑weight models, CPT improves factual recall without catastrophic forgetting, while the cost is negligible and data quality outweighs quantity. The study identifies optimal learning rates, shows LoRA can match full CPT, and demonstrates that CPT gains transfer to fine‑tuned models.
arXiv AI
Sep 16
Attention is All You Need Until You Need Retention
arXiv:2501.09166v2 Announce Type: replace-cross Abstract: Pretrained Transformers keep what they learned in their weights and lose what they observe once a session ends. The first version of this pap...