arXiv:2606. 08167v1 Announce Type: cross Abstract: Recent research has established empirical scaling laws to predict model performance on multi-domain data mixtures.
arXiv:2609.38011v1 Announce Type: new Abstract: Modern machine learning systems are trained on mixtures of data from different domains, and choosing the right mixture can substantially improve downst...
arXiv:2607. 11052v1 Announce Type: new Abstract: Machine learning progress is often attributed to scaling model size and dataset volume, yet the composition of data can be just as consequential.
arXiv:2607. 22769v1 Announce Type: cross Abstract: The training efficacy of large language models (LLMs) is fundamentally constrained by the quality and composition of training data.
arXiv:2608. 14071v1 Announce Type: new Abstract: As large language models scale, their training-token budgets must also increase to maintain an appropriate tokens-per-parameter ratio (\(\mathrm{TPP}\)).
The article proposes treating large language model (LLM) data mixing as a classical mixture experiment, where data domains are components, token shares are proportions, and proxy-training runs serve as design points. Using sparse second‑order Scheffé response‑surface models, the authors construct model‑robust Σ‑optimal designs that efficiently identify optimal data mixtures and reveal strong interaction effects, especially between weak domains and web‑derived text. Empirical results on RegMix show that these designs recover mixture rankings while reducing proxy runs by about 25%, demonstrating that data mixing can be optimized through experimental design rather than solely prediction.
arXiv:2605. 29548v2 Announce Type: replace Abstract: Larger models learn tasks smaller models do not.
arXiv:2609.09572v1 Announce Type: new Abstract: Synthetic data has become a promising way to scale model training beyond limited human-generated data but it may also induce strong model collapse (Doh...
arXiv:2608. 20061v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures significantly expand model capacity without a proportional increase in computational cost.
arXiv:2512. 22088v3 Announce Type: replace-cross Abstract: The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improvements in model performance with increasing computational resources.
The paper introduces a new closed‑form scaling law that extends Chinchilla’s original formula to handle data‑constrained regimes. It decomposes loss into undercapacity, undertraining, and overfitting components, saturating between an irreducible loss and an uninformed baseline. The authors validate the model on diverse architectures and domains, achieving state‑of‑the‑art RMSE across multiple LLM scaling‑law grids and enabling cost‑aware training allocations.
arXiv:2606. 06888v1 Announce Type: new Abstract: Classical scaling laws for language model pretraining balance model size against training dataset size under a fixed compute budget, assuming abundant data and a single pass over the corpus.
arXiv:2606. 07597v1 Announce Type: cross Abstract: Pre-training data mixtures are commonly tuned by running small-scale experiments and extrapolating to the target training budget.