Nemotron-RL-instruction_following-structured_outputs

## Dataset Description:

The Nemotron-RL-instruction_following-structured_outputs dataset tests the ability of the model to follow output formatting instructions under schema constraints under the JSON format. Each problem consists of three components: The document, output formatting Instruction (Schema), and question. The dataset varies the difficulty of each problem by varying the location of instructions, the comprehensiveness of instructions, the complexity of the schema, and the type of document/user message.

This dataset is released as part of NVIDIA [NeMo Gym](https://github.com/NVIDIA-NeMo/Gym), a framework for building reinforcement learning environments to train large language models. NeMo Gym contains a growing collection of training environments and datasets to enable Reinforcement Learning from Verifiable Reward (RLVR).

NeMo Gym is an open-source library within the [NVIDIA NeMo framework](https://github.com/NVIDIA-NeMo/), NVIDIA's GPU accelerated, end-to-end training framework for large language models (LLMs), multi-modal models and speech models.

This dataset is part of the [Nemo Gym Collection](https://huggingface.co/collections/nvidia/nemo-gym).

This dataset is ready for commercial use.

## Dataset Owner(s):
NVIDIA Corporation

## Dataset Creation Date:
October 2025

## License/Terms of Use:
CC BY 4.0

## Intended Usage:
To be used with [NeMo Gym](https://github.com/NVIDIA-NeMo/Gym) for post-training LLMs.

## Dataset Characterization
Data Collection Method<br>
* Seed [Synthetic] <br>
* Prompts [Synthetic] <br>

Labeling Method<br>
* [Synthetic] <br>

## Dataset Format
Text Only, Compatible with [NeMo Gym](https://github.com/NVIDIA-NeMo/Gym)

## Dataset Quantification
Record Count: Train: 9437 prompts, Validation: 512 prompts (Total 9949 prompts).
Feature Count: 4 (responses_create_params, schema_type, schema_fields_count)
Measurement of Total Data Storage: Train: 86.77 MiB, Validation: 4.70 MiB(Total 91.47 MiB)

## Reference(s):
[NeMo Gym](https://github.com/NVIDIA-NeMo/Gym)

## Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

## 数据集描述：
Nemotron-RL-instruction_following-structured_outputs数据集用于测试模型在JSON格式的Schema约束下遵循输出格式指令的能力。每个问题包含三个组成部分：文档、输出格式指令（Schema）与问题。本数据集通过调整指令的位置、指令的完备性、Schema的复杂度以及文档/用户消息的类型来调整每个问题的难度。

本数据集作为NVIDIA的[NeMo Gym](https://github.com/NVIDIA-NeMo/Gym)的一部分发布，该框架用于构建用于训练大语言模型的强化学习环境。NeMo Gym收录了不断扩充的训练环境与数据集，以支持可验证奖励强化学习（Reinforcement Learning from Verifiable Reward，RLVR）。

NeMo Gym是[NVIDIA NeMo框架](https://github.com/NVIDIA-NeMo/)下的开源库，该框架是NVIDIA推出的GPU加速型端到端训练框架，可用于大语言模型（LLMs）、多模态模型与语音模型的训练。

本数据集隶属于[NeMo Gym数据集合集](https://huggingface.co/collections/nvidia/nemo-gym)。

本数据集可商用。

## 数据集所有者：
NVIDIA Corporation

## 数据集创建日期：
2025年10月

## 许可/使用条款：
CC BY 4.0

## 预期用途：
需配合[NeMo Gym](https://github.com/NVIDIA-NeMo/Gym)用于大语言模型的后训练环节。

## 数据集特征
数据收集方法
* 种子数据（合成数据）
* 提示词（合成数据）

标注方法
* 合成数据标注

## 数据集格式
纯文本格式，兼容[NeMo Gym](https://github.com/NVIDIA-NeMo/Gym)

## 数据集量化统计
样本数量：训练集：9437条提示词，验证集：512条提示词（总计9949条提示词）。
特征数量：4项（responses_create_params、schema_type、schema_fields_count）
总数据存储量：训练集：86.77 MiB，验证集：4.70 MiB（总计91.47 MiB）

## 参考文献：
[NeMo Gym](https://github.com/NVIDIA-NeMo/Gym)

## 伦理考量：
NVIDIA认为，可信人工智能（Trustworthy AI）是一项共同责任，我们已制定相关政策与实践规范，以支持各类人工智能应用的开发。开发者在按照服务条款下载或使用本模型时，应与内部模型团队协作，确保该模型符合相关行业与应用场景的要求，并应对可能出现的产品误用问题。
请提交模型质量、风险、安全漏洞或NVIDIA人工智能相关问题反馈至[此处](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).