Synthetic Data Characterization via Training Dynamics

Synthetic data now is essential to LLM training, used to strengthen advanced capabilities such as autonomous and long-horizon task execution. Yet recent work shows that training on it at scale can degrade model generation, making it important to decide what synthetic data is worth training on. While current data curation practices do so with individual-level signals (i.e., estimates of each data sample's training utility in isolation), across pre-training and post-training settings we show that this is insufficient for synthetic data, and that group-level signals (i.e., estimates of utility that account for interactions among data samples) are necessary for effective data curation. First, we show that individual-level signals are blind to how samples jointly affect training: synthetic datasets with different compositions can be indistinguishable under individual-level influence yet differ sharply under group-level influence, and curating by the latter yields better downstream performance, particularly in generative capability. Second, we find that group-level signals matter more as training pipelines become increasingly synthetic: among widely used data curation methods, only those incorporating them improve over baseline, with gains increasing when weights capturing relations among samples are amplified. Finally, we translate these findings into practice -- for model developers under a compute budget, we offer a cheap diagnostic that prioritizes which groups of synthetic data most need group-level estimation, recovering much of the benefit of full group-level scoring at a fraction of the compute cost.

Synthetic data are increasingly used to scale LLM training, yet more synthetic data do not necessarily produce better models. Useful synthetic data must add information relevant to the target task without introducing errors that offset their benefit, and the value of an example can change as the training set grows. We develop a linear theory that characterizes this tradeoff and determines where synthetic data are useful, how much should be added, and the marginal value of adding one example to an existing set. The analysis shows the conditions when input coverage alone is sufficient and when synthetic errors must also be considered. Guided by these results, we introduce \emph{Training-Aware Target Coverage} (TATC), a synthetic data selection method for LLM fine-tuning. TATC identifies candidates whose training effects are beneficial to the target task and selects among them to expand coverage of target-relevant directions not already represented by the available data. Experiments on text and image data verify the linear theory. With mathematical reasoning tasks, TATC selects synthetic solutions for fine-tuning Qwen2.5-Math-1.5B-Instruct and outperforms alternative synthetic-data selection methods on GSM8K across selection budgets. In summary, we provide a principled approach to synthetic data selection by quantifying and maximizing its value to the target task.

Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic account of this inconsistency: synthetic data improves a model only when the generation-training loop is information-open, i.e., shaped by external signals (verifiers, environments, or rubrics) that inject task-relevant information beyond the model's current distribution. When the loop is information-closed (relying on the model's own outputs without such signals), the data processing inequality ensures that task-relevant information can only decrease, making collapse a predicted outcome. Among information-open pipelines, both efficiency and generalization hinge on the meta-level of supervision: a coarser signal such as binary correctness treats all acceptable outputs as equivalent, so the behavior it teaches is not tied to any particular domain or surface form and generalizes naturally across tasks and domains. These observations lead to a guiding thesis: learning preferentially converges to the most information-efficient signal component available, which accelerates learning when that component is the intended one, but causes reward hacking when a spurious pattern happens to be simpler.