AquilaMed-RL

## Introduce

This dataset is used for the human preference training stage. The data is sampled from the SFT dataset, and the sampled data is then inferred using a trained SFT model and GPT-4. GPT-4 is subsequently used to score the two responses to determine the positive and negative examples.

## Cite

If you find our work helpful, feel free to give us a cite.

```
@misc{zhao2024aquliamed,
title={Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models},
author={Lulu Zhao and Weihao Zeng and Xiaofeng Shi and Hua Zhou and Donglin Hao and Yonghua Lin},
year={2024},
eprint={2406.12182},
archivePrefix={arXiv},
primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
}
```

## 数据集介绍
本数据集用于人类偏好训练阶段。数据从监督微调（Supervised Fine-Tuning，SFT）数据集采样得到，随后使用已训练的SFT模型与GPT-4对采样所得数据进行推理，生成两份回复。后续再通过GPT-4对这两份回复进行评分，以此确定正负样本。

## 引用说明
若您认为本工作对您有所助益，请引用我们的研究。

@misc{zhao2024aquliamed,
title={Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models},
author={Lulu Zhao and Weihao Zeng and Xiaofeng Shi and Hua Zhou and Donglin Hao and Yonghua Lin},
year={2024},
eprint={2406.12182},
archivePrefix={arXiv},
primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
}