# Data for the paper "Self-critiquing models for assisting human evaluators"

For any questions, contact jeffwu@openai.com.

## Training dataset

Our dataset is released at the folder: `https://openaipublic.blob.core.windows.net/critiques/dataset/`.
There are six different files:
- [base/train.jsonl.gz]{https://openaipublic.blob.core.windows.net/critiques/dataset/base/train.jsonl.gz}
- [base/test.jsonl.gz]{https://openaipublic.blob.core.windows.net/critiques/dataset/base/test.jsonl.gz}
- [critiques/train.jsonl.gz]{https://openaipublic.blob.core.windows.net/critiques/dataset/critiques/train.jsonl.gz}
- [critiques/test.jsonl.gz]{https://openaipublic.blob.core.windows.net/critiques/dataset/critiques/test.jsonl.gz}
- [helpfulness/train.jsonl.gz]{https://openaipublic.blob.core.windows.net/critiques/dataset/helpfulness/train.jsonl.gz}
- [helpfulness/test.jsonl.gz]{https://openaipublic.blob.core.windows.net/critiques/dataset/helpfulness/test.jsonl.gz}

## Assistance results dataset
We release results from our assistance experiments at `https://openaipublic.blob.core.windows.net/critiques/assistance.jsonl.gz`.

## Example download commands

```bash
for round in base critiques helpfulness; do
  mkdir -p dataset/$round
  for split in train test; do
    curl "https://openaipublic.blob.core.windows.net/critiques/dataset/$round/$split.jsonl.gz" > dataset/$round/$split.jsonl.gz
  done
done
```

```bash
curl -O 'https://openaipublic.blob.core.windows.net/critiques/assistance.jsonl.gz'
```