相关论文: Characterizing Model Behavior Under Synthetic Data…

Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large multimodal models (LMMs) due to the relative scarcity of…

Large language models (LLMs) have great potential for synthetic data generation. This work shows that useful data can be synthetically generated even for tasks that cannot be solved directly by LLMs: for problems with structured outputs, it…

While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement learning (RL) post-training remains largely unexplored. This paper presents a systematic empirical…

Large language models (LLMs) have demonstrated strong capabilities in programming and mathematical reasoning tasks, but are constrained by limited high-quality training data. Synthetic data can be leveraged to enhance fine-tuning outcomes,…

Large language models (LLMs) can be leveraged to help with writing formulas in spreadsheets, but resources on these formulas are scarce, impacting both the base performance of pre-trained models and limiting the ability to fine-tune them.…

Mathematical reasoning remains a challenging area for large language models (LLMs), prompting the development of math-specific LLMs such as LLEMMA, DeepSeekMath, and Qwen2-Math, among others. These models typically follow a two-stage…

The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…

A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are…

Large Language Models (LLMs) have democratized synthetic data generation, which in turn has the potential to simplify and broaden a wide gamut of NLP tasks. Here, we tackle a pervasive problem in synthetic data generation: its generative…

*Data Synthesis* is a promising way to train a small model with very little labeled data. One approach for data synthesis is to leverage the rich knowledge from large language models to synthesize pseudo training examples for small models,…

Mathematical reasoning is a challenging task for large language models (LLMs), while the scaling relationship of it with respect to LLM capacity is under-explored. In this paper, we investigate how the pre-training loss, supervised data…

Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation. Despite these benefits, the efficiency of…

As synthetic data becomes widely used in language model development, understanding its impact on model behavior is crucial. This paper investigates the impact of the diversity of sources of synthetic data on fine-tuned large language…

Classification Models use input data to predict the likelihood that the subsequent input data will fall into predetermined categories. To perform effective classifications, these models require large datasets for training. It is becoming…

Competitive programming poses a significant challenge for Code LLMs. While recent models have shown promise, they heavily rely on finite real-world data, raising concerns about scalability and contamination. In this paper, we investigate a…

An increasingly common practice is to train large language models (LLMs) using synthetic data. Often this synthetic data is produced by the same or similar LLMs as those it is being used to train. This raises the question of whether the…

Inspired by the principle of deliberate practice in human learning, we propose Deliberate Practice for Synthetic Data Generation (DP), a novel framework that improves sample efficiency through dynamic synthetic data generation. Prior work…

Differentially private training algorithms like DP-SGD protect sensitive training data by ensuring that trained models do not reveal private information. An alternative approach, which this paper studies, is to use a sensitive dataset to…

The reasoning capabilities of Large Language Models (LLMs) play a critical role in many downstream tasks, yet depend strongly on the quality of training data. Despite various proposed data construction methods, their practical utility in…

Alongside the growth of generative AI, we are witnessing a surge in the use of synthetic data across all stages of the AI development pipeline. It is now common practice for researchers and practitioners to use one large generative model…