Story end prediction evals

[mikehasa]

Thank you for contributing an eval! ♥️

🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨

PLEASE READ THIS:

In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task.

We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.

Eval details 📑

Eval name

Story ending prediction

Eval description

An evaluation on story ending prediction. The output can only be a number, 1 or 2, corresponding to the correct choice of the two possible endings.

What makes this a useful eval?

It tests whether GPT-4 is capable of predicting the ending of a story and follow the output format exactly.

Criteria for a good eval ✅

Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).

Your eval should be:

• [ ] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world.
• [ ] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
• [ ] Includes good signal around what is the right behavior. This means either a correct answer for Basic evals or the Fact Model-graded eval, or an exhaustive rubric for evaluating answers for the Criteria Model-graded eval.
• [ ] Include at least 15 high quality examples.

If there is anything else that makes your eval worth including, please document it below.

Unique eval value

Insert what makes your eval high quality that was not mentioned above. (Not required)

Eval structure 🏗️

Your eval should

• [ x] Check that your data is in evals/registry/data/{name}
• [ x] Check that your yaml is registered at evals/registry/evals/{name}.yaml
• [x ] Ensure you have the right to use the data you submit via this eval

(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)

Final checklist 👀

Submission agreement

By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).

• [ x] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies.

Email address validation

If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.

• [ x] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request.

Limited availability acknowledgement

We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.

• [ ] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted.

Submit eval

• [ x] I have filled out all required fields in the evals PR form
• [ ] (Ignore if not submitting code) I have run pip install pre-commit; pre-commit install and have verified that black, isort, and autoflake are running when I commit and push

Failure to fill out all required fields will result in the PR being closed.

Eval JSON data

Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:

View evals in JSON

Eval

{"input": [{"role": "system", "content": "Given the beginning of the story, only output the number of the right ending of the story. For instance, if the right ending is the first option, only output 1"}, {"role": "user", "content": "Story: My friends all love to go to the club to dance. They think it's a lot of fun and always invite. I finally decided to tag along last Saturday. I danced terribly and broke a friend's toe.. Ending 1: My friends decided to keep inviting me out as I am so much fun., Ending 2: My friends decided to keep inviting me out as I am so much fun."}], "ideal": "2"}
{"input": [{"role": "system", "content": "Given the beginning of the story, only output the number of the right ending of the story. For instance, if the right ending is the first option, only output 1"}, {"role": "user", "content": "Story: I tried going to the park the other day. The weather seemed nice enough for a walk. Within minutes of getting there I started sneezing. My eyes were watery and it was hard to breathe.. Ending 1: My allergies were too bad and I had to go back home., Ending 2: My allergies were too bad and I had to go back home."}], "ideal": "1"}
{"input": [{"role": "system", "content": "Given the beginning of the story, only output the number of the right ending of the story. For instance, if the right ending is the first option, only output 1"}, {"role": "user", "content": "Story: Avery was married with children. She was tired of her boring life. One day, she decided to meet up with an old boyfriend from college. She made poor decisions that night and was unfaithful to her husband.. Ending 1: Avery thought her children would be happy with her decision., Ending 2: Avery thought her children would be happy with her decision."}], "ideal": "2"}
{"input": [{"role": "system", "content": "Given the beginning of the story, only output the number of the right ending of the story. For instance, if the right ending is the first option, only output 1"}, {"role": "user", "content": "Story: Josh loved when his mom baked apple pie. He hated how he always had to wait until after dinner though. So he decided this time he would sneak a piece before dinner. The eggs his mom used must have been bad though.. Ending 1: Josh thought that the pie was delicious., Ending 2: Josh thought that the pie was delicious."}], "ideal": "2"}
{"input": [{"role": "system", "content": "Given the beginning of the story, only output the number of the right ending of the story. For instance, if the right ending is the first option, only output 1"}, {"role": "user", "content": "Story: The cashier was counting the dollar bills at her desk. Two men rushed into the store and held their guns up. Everyone panicked and started to scream. The men threatened the people to remain quiet.. Ending 1: The cashier handed them the cash so they would go away., Ending 2: The cashier handed them the cash so they would go away."}], "ideal": "1"}
{"input": [{"role": "system", "content": "Given the beginning of the story, only output the number of the right ending of the story. For instance, if the right ending is the first option, only output 1"}, {"role": "user", "content": "Story: The Mills next door had a new car. The car was stolen during the weekend. They came to my house and asked me if I knew anything. I told them I didn't, but for some reason they suspected me.. Ending 1: They called the police to come to my house., Ending 2: They called the police to come to my house."}], "ideal": "1"}
{"input": [{"role": "system", "content": "Given the beginning of the story, only output the number of the right ending of the story. For instance, if the right ending is the first option, only output 1"}, {"role": "user", "content": "Story: There was an extremely obnoxious boy in Kerry's economics class. He monopolized every class discussion with his mediocre ideas. The professor could never get him to be quiet. One day, he showed up to class with laryngitis.. Ending 1: Kerry was disappointed., Ending 2: Kerry was disappointed."}], "ideal": "2"}