Magpie-Pro-DPO-100K-v0.1


Project Web: [https://magpie-align.github.io/](https://magpie-align.github.io/)

Arxiv Technical Report: [https://arxiv.org/abs/2406.08464](https://arxiv.org/abs/2406.08464)

Codes: [https://github.com/magpie-align/magpie](https://github.com/magpie-align/magpie)

## Abstract
<details><summary>Click Here</summary>
High-quality instruction data is critical for aligning large language models (LLMs). Although some models, such as Llama-3-Instruct, have open weights, their alignment data remain private, which hinders the democratization of AI. High human labor costs and a limited, predefined scope for prompting prevent existing open-source data creation methods from scaling effectively, potentially limiting the diversity and quality of public alignment datasets. Is it possible to synthesize high-quality instruction data at scale by extracting it directly from an aligned LLM? We present a self-synthesis method for generating large-scale alignment data named Magpie. Our key observation is that aligned LLMs like Llama-3-Instruct can generate a user query when we input only the left-side templates up to the position reserved for user messages, thanks to their auto-regressive nature. We use this method to prompt Llama-3-Instruct and generate 4 million instructions along with their corresponding responses. We perform a comprehensive analysis of the extracted data and select 300K high-quality instances. To compare Magpie data with other public instruction datasets, we fine-tune Llama-3-8B-Base with each dataset and evaluate the performance of the fine-tuned models. Our results indicate that in some tasks, models fine-tuned with Magpie perform comparably to the official Llama-3-8B-Instruct, despite the latter being enhanced with 10 million data points through supervised fine-tuning (SFT) and subsequent feedback learning. We also show that using Magpie solely for SFT can surpass the performance of previous public datasets utilized for both SFT and preference optimization, such as direct preference optimization with UltraFeedback. This advantage is evident on alignment benchmarks such as AlpacaEval, ArenaHard, and WildBench.
</details><be>

## Dataset Details
This dataset is generated by [Llama 3 70B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) for direct preference optimization.

To create the dataset, we first selected 100K high-quality Magpie instructions with diverse task categories, then generated responses using [Llama 3 70B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) 5 times for each instruction, using a temperature of 0.8. We then annotated RM scores using RLHFlow/ArmoRM-Llama3-8B-v0.1, labeling the response with the highest RM score as the chosen response, and the one with the lowest RM score as the rejected response.

## 📚 Citation

If you find the model, data, or code useful, please cite our paper:
```
@article{xu2024magpie,
title={Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing},
author={Zhangchen Xu and Fengqing Jiang and Luyao Niu and Yuntian Deng and Radha Poovendran and Yejin Choi and Bill Yuchen Lin},
year={2024},
eprint={2406.08464},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```

Please also cite the reward model for creating preference datasets:

ArmoRM paper:
```
@article{wang2024interpretable,
title={Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts},
author={Wang, Haoxiang and Xiong, Wei and Xie, Tengyang and Zhao, Han and Zhang, Tong},
journal={arXiv preprint arXiv:2406.12845},
year={2024}
}
```

**Questions?** Please contact [Zhangchen](https://zhangchenxu.com/) by email.


项目主页：[https://magpie-align.github.io/](https://magpie-align.github.io/)
arXiv 技术报告：[https://arxiv.org/abs/2406.08464](https://arxiv.org/abs/2406.08464)
代码仓库：[https://github.com/magpie-align/magpie](https://github.com/magpie-align/magpie)

## 摘要
<details><summary>点击展开</summary>
高质量指令数据对于对齐大语言模型（Large Language Model，LLM）至关重要。尽管部分模型（如Llama-3-Instruct）已开源权重，但其对齐数据仍处于私有状态，这阻碍了人工智能的民主化进程。当前开源数据构建方法面临人工成本高昂、提示范围预先限定且有限等问题，难以实现有效扩展，进而可能限制了公开对齐数据集的多样性与质量。能否直接从已对齐的大语言模型中提取信息，大规模合成高质量指令数据？为此，我们提出了一种用于生成大规模对齐数据的自合成方法，命名为Magpie。我们的核心观察在于：得益于自回归特性，仅向Llama-3-Instruct等已对齐模型输入用户消息预留位置之前的左侧模板时，模型即可生成用户查询。我们利用该方法对Llama-3-Instruct进行提示，生成了400万条指令及其对应回复。我们对提取的数据进行了全面分析，并从中筛选出30万条高质量样本。为了将Magpie数据集与其他公开指令数据集进行对比，我们分别使用各数据集对Llama-3-8B-Base进行微调，并评估微调后模型的性能。实验结果表明，在部分任务中，使用Magpie数据集微调的模型性能可与官方Llama-3-8B-Instruct相媲美——尽管后者通过监督微调（Supervised Fine-Tuning，SFT）与后续反馈学习，使用了1000万条数据进行增强。我们还证明，仅使用Magpie数据集进行监督微调，其性能便可超越此前同时用于监督微调与偏好优化的公开数据集（如基于UltraFeedback的直接偏好优化（Direct Preference Optimization）数据集）。这一优势在AlpacaEval、ArenaHard与WildBench等对齐基准测试中均有体现。
</details><br>

## 数据集详情
本数据集由[Llama 3 70B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)生成，用于直接偏好优化任务。
为构建该数据集，我们首先筛选出10万条覆盖多样任务类别的高质量Magpie指令，随后针对每条指令使用[Llama 3 70B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)生成5条回复，温度系数设置为0.8。接下来，我们使用RLHFlow/ArmoRM-Llama3-8B-v0.1标注奖励模型（Reward Model，RM）得分，将RM得分最高的回复标记为“选中回复”，得分最低的回复标记为“被拒绝回复”。

## 📚 引用
若您认为本模型、数据集或代码对您的研究有所帮助，请引用如下论文：

@article{xu2024magpie,
title={Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing},
author={Zhangchen Xu and Fengqing Jiang and Luyao Niu and Yuntian Deng and Radha Poovendran and Yejin Choi and Bill Yuchen Lin},
year={2024},
eprint={2406.08464},
archivePrefix={arXiv},
primaryClass={cs.CL}
}

请同时引用用于创建偏好数据集的奖励模型相关论文：
ArmoRM论文：

@article{wang2024interpretable,
title={Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts},
author={Wang, Haoxiang and Xiong, Wei and Xie, Tengyang and Zhao, Han and Zhang, Tong},
journal={arXiv preprint arXiv:2406.12845},
year={2024}
}

**疑问与沟通？** 请通过邮件联系[张晨（Zhangchen）](https://zhangchenxu.com/).