shuyuej/GSM8K-Consistency
收藏Hugging Face2023-12-31 更新2024-03-04 收录
下载链接：
https://hf-mirror.com/datasets/shuyuej/GSM8K-Consistency
下载链接
链接失效反馈官方服务：
资源简介：
---
license: apache-2.0
---
# GSM8K-Consistency Benchmark
**GSM8K-Consistency** is a benchmark database for analyzing the consistency of `Arithmetic Reasoning on GSM8K`.
## 🚀 The dataset is available on 🤗 Hugging Face!
This is a math-problem-related semantics-preserving perturbation benchmark that can be very helpful for evaluating the consistency of arithmetic reasoning capability.
## 💻 Dataset Usage
Run the following command to load the data:
```python
from datasets import load_dataset
dataset = load_dataset("shuyuej/GSM8K-Consistency")
dataset = dataset['train']
print(dataset)
```
Dataset Description:
```python
Dataset({
features: ['id', 'original_question', 'paraphrased_question', 'answer_detail', 'numerical_answer'],
num_rows: 85225
})
```
提供机构：
shuyuej
原始信息汇总
GSM8K-Consistency Benchmark
GSM8K-Consistency 是一个用于分析 GSM8K 算术推理 一致性的基准数据库。
数据集描述
该数据集是一个与数学问题相关的语义保持扰动基准，有助于评估算术推理能力的一致性。
数据集使用
使用以下命令加载数据： python from datasets import load_dataset
dataset = load_dataset("shuyuej/GSM8K-Consistency") dataset = dataset[train] print(dataset)
数据集结构
python Dataset({ features: [id, original_question, paraphrased_question, answer_detail, numerical_answer], num_rows: 85225 })
