FinEval

# 💰 Demystifying Domain-adaptive Post-training for Financial LLMs

This is the **evaluation data** used in the recipe described in our paper:
📄 [*Demystifying Domain-adaptive Post-training for Financial LLMs*](https://arxiv.org/abs/2501.04961)

For more details, please check the following resources:

- 🌐 **Project Page:** [https://vincent950129.github.io/adapt-llm/](https://vincent950129.github.io/adapt-llm/)
- 📚 **Trained Model:** [https://huggingface.co/Salesforce/Llama-Fin-8b](https://huggingface.co/Salesforce/Llama-Fin-8b)
- 🧠 **Training Data:** [https://huggingface.co/datasets/Salesforce/FinTrain](https://huggingface.co/datasets/Salesforce/FinTrain)
- 💻 **Code Repository:** [https://github.com/SalesforceAIResearch/FinDAP](https://github.com/SalesforceAIResearch/FinDAP)

### Ethical Considerations
Users need to make their own assessment regarding any obligations or responsibilities under the corresponding licenses or terms and conditions pertaining to the original datasets and data. This release is for research purposes only in support of an academic paper.

## Citation

If you find our project helpful, please consider citing our paper 😊

```
@misc{ke2025demystifyingdomainadaptiveposttrainingfinancial,
title={Demystifying Domain-adaptive Post-training for Financial LLMs},
author={Zixuan Ke and Yifei Ming and Xuan-Phi Nguyen and Caiming Xiong and Shafiq Joty},
year={2025},
eprint={2501.04961},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2501.04961},
}
```

💰 揭开金融大语言模型（Large Language Model，LLM）领域自适应后训练的神秘面纱
本数据集为对应论文中所述研究方案配套的**评测数据**，相关论文为：
📄 [《揭开金融大语言模型领域自适应后训练的神秘面纱》](https://arxiv.org/abs/2501.04961)

如需获取更多细节，请查阅以下资源：
- 🌐 **项目主页**：[https://vincent950129.github.io/adapt-llm/](https://vincent950129.github.io/adapt-llm/)
- 📚 **已训练模型**：[https://huggingface.co/Salesforce/Llama-Fin-8b](https://huggingface.co/Salesforce/Llama-Fin-8b)
- 🧠 **训练数据集**：[https://huggingface.co/datasets/Salesforce/FinTrain](https://huggingface.co/datasets/Salesforce/FinTrain)
- 💻 **代码仓库**：[https://github.com/SalesforceAIResearch/FinDAP](https://github.com/SalesforceAIResearch/FinDAP)

### 伦理考量
用户需自行评估与原始数据集及相关数据对应的许可协议、条款条件相关的任何义务或责任。本数据集仅用于支持学术论文的研究用途。

## 引用
若您认为本项目对您的研究有所帮助，请考虑引用我们的论文 😊

@misc{ke2025demystifyingdomainadaptiveposttrainingfinancial,
title={Demystifying Domain-adaptive Post-training for Financial LLMs},
author={Zixuan Ke and Yifei Ming and Xuan-Phi Nguyen and Caiming Xiong and Shafiq Joty},
year={2025},
eprint={2501.04961},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2501.04961},
}

搜集汇总

背景与挑战

背景概述

FinEval是一个用于金融大语言模型领域自适应后训练的评估数据集，源自Salesforce的研究论文。它提供了评估金融模型性能的标准数据，并关联了项目页面、训练模型和训练数据等资源。