mir/gpt-2-output-dataset
2
0
Fork 0
mirror of https://github.com/openai/gpt-2-output-dataset synced 2025-08-29 13:28:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

initial analysis

Browse Source
This commit is contained in:
Alec 2019-05-03 15:53:48 -07:00
parent 9972fb3941
commit f5b5065025
1 changed files with 15 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
README.md
View File

@ -1,14 +1,14 @@
# gpt-2-output-dataset # gpt-2-output-dataset
This dataset contains: This dataset contains:
- 250K samples from the WebText test set - 250K documents from the WebText test set
- For each GPT-2 model (trained on the WebText training set), 250K plain samples (temperature 1, no truncation) and 250K samples generated with top-k 40 truncation - For each GPT-2 model (trained on the WebText training set), 250K random samples (temperature 1, no truncation) and 250K samples generated with Top-K 40 truncation
We look forward to the research produced using this data! We look forward to the research produced using this data!
### Download ### Download
For each, we have a training split of 500K total examples, as well as validation and test splits of 10K examples. For each model, we have a training split of 250K generated examples, as well as validation and test splits of 5K examples.
All data is located in Google Cloud Storage, at under the directory `gs://gpt-2/output-dataset/v1`. All data is located in Google Cloud Storage, at under the directory `gs://gpt-2/output-dataset/v1`.
@ -30,7 +30,7 @@ We've provided a script to download all of them, in `download_dataset.py`.
### Detectability baselines ### Detectability baselines
We're interested in seeing research in detectability of our model generations. We're interested in seeing research in detectability of GPT-2 model family generations.
We've provided a starter baseline which trains a logistic regression detector on TF-IDF unigram and bigram features, in `baseline.py`. We've provided a starter baseline which trains a logistic regression detector on TF-IDF unigram and bigram features, in `baseline.py`.
@ -41,6 +41,16 @@ We've provided a starter baseline which trains a logistic regression detector on
| 762M | 77.16% | 94.43% | | 762M | 77.16% | 94.43% |
| 1542M | 74.31% | 92.69% | | 1542M | 74.31% | 92.69% |
### Initial Analysis
![Impact of Document Length](https://i.imgur.com/PZ3GOeS.png)
Shorter documents are harder to detect. Accuracy of detection of a short documents of 500 characters (a long paragraph) is about 15% lower.
![Part of Speech Analysis](https://i.imgur.com/eH9Ogqo.png)
Truncated sampling, which is commonly used for high-quality generations from the GPT-2 model family, results in a shift in the part of speech distribution of the generated text compared to real text. A clear example is the underuse of proper nouns and overuse of pronouns which are more generic. This shift contributes to the 8% to 18% higher detection rate of Top-K samples compared to random samples across models.
### Data removal requests ### Data removal requests
If you believe your work is included in our dataset and would like us to remove it, please let us know at webtextdata@openai.com. If you believe your work is included in WebText and would like us to remove it, please let us know at webtextdata@openai.com.