# SCER

**Repository Path**: ForeverMeteor/SCER

## Basic Information

- **Project Name**: SCER
- **Description**: SCER的官方代码仓库
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-04-09
- **Last Updated**: 2025-05-24

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Self-Consistency, Extract and Rectify: Knowledge Graph Enhance Large Language Model for Electric Power Question Answering

这是论文**Self-Consistency, Extract and Rectify: Knowledge Graph Enhance Large Language Model for Electric Power Question Answering**（SCER）的官方仓库。

## 安装需求

``` pip
pip install -r requirement.txt
```

## 运行实验

1. 将评估数据集放于data/eval下；将图数据集放于data/graph下

2. 将自己的镜像网站填入CONSTANT的url变量中，API_KEY填入CONSTANT的api_key变量中

3. 依次运行SC_only.py、KB_only.py，结果将储存至result中

关于第2步：若要运行调用接口的模型则按原文操作；若要自行部署模型，则：

1. 在self_consistency文件夹下增加新类并继承SelfConsistency类

2. 按照已有ChatGLM的模板自行实现调用自己的PLM

## 引用

引用本文：
```bibtex
@inproceedings{zhao2024self,
  title={Self-consistency, Extract and Rectify: Knowledge Graph Enhance Large Language Model for Electric Power Question Answering},
  author={Zhao, Jinxiong and Ma, Zhicheng and Zhao, Hong and Zhang, Xun and Liu, Qichuan and Zhang, Chentao},
  booktitle={International Conference on Intelligent Computing},
  pages={493--504},
  year={2024},
  organization={Springer}
}
```

## 致谢

本文灵感来源于CoT, SC和RR。
```bibtex
@article{wei2022chain,
  title={Chain-of-thought prompting elicits reasoning in large language models},
  author={Wei, Jason and Wang, Xuezhi and Schuurmans, Dale and Bosma, Maarten and Xia, Fei and Chi, Ed and Le, Quoc V and Zhou, Denny and others},
  journal={Advances in neural information processing systems},
  volume={35},
  pages={24824--24837},
  year={2022}
}
```

```bibtex
@article{wang2022self,
  title={Self-consistency improves chain of thought reasoning in language models},
  author={Wang, Xuezhi and Wei, Jason and Schuurmans, Dale and Le, Quoc and Chi, Ed and Narang, Sharan and Chowdhery, Aakanksha and Zhou, Denny},
  journal={arXiv preprint arXiv:2203.11171},
  year={2022}
}
```

```bibtex
@article{he2022rethinking,
  title={Rethinking with retrieval: Faithful large language model inference},
  author={He, Hangfeng and Zhang, Hongming and Roth, Dan},
  journal={arXiv preprint arXiv:2301.00303},
  year={2022}
}
```