Duplicate Question Eval

[acrylic-style]

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

Duplicate Question

Eval description

Checks if the two questions are paraphrases of each other (have the same meaning).

What makes this a useful eval?

In forum-like websites, they would be able to automatically detect if two questions are duplicates.

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:

• [x] 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.
• [x] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
• [x] 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.
• [x] 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

With gpt-3.5-turbo: Final report: {'accuracy': 0.2}

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.

• [x] 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
• [x] (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": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) I tried to connect to your Foobar server with the Foobar client, but after a while joined the server, the server lags and eventually kicks me with the reason \"Timed out\". How can I fix this?\nb) I can't connect to your Foobar server with the Foobar client and I don't know why. How can I fix this?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) I had linked my Foo account for the Bar account, but it got suddenly unlinked and I can't log in anymore. How do I recover the Bar account?\nb) My linked Foo account got deactivated and now I can't log in to the Bar account. How do I recover my both accounts?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) Do you need friends?\nb) Why do we need friends?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) Is Foobar useful for work?\nb) What is Foobar? Is it useful?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) How do I start selling my items on Foobar?\nb) How do I sell my bells on Foobar?"}], "ideal": "Y"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) How do I contact a hacker?\nb) How do I contact a legit hacker?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) Can I restore my deleted emails from a Foobar account?\nb) How can I recover my old mail from a Foobar account?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) How much do websites earn on clicks?\nb) How do websites earn?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) What is the difference between the while and do while loop in C?\nb) What is the difference between for, while, and do while loop in C?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) How can I overcome my depression and my fears?\nb) What is the best way to overcome depression without doing anything?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) Does chocolate expire?\nb) Does chocolate get stale?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) How to gain weight?\nb) How can I gain weight but also eat healthy?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) Does OpenAI rotate API keys?\nb) Does OpenAI rotate API keys if they found has leaked publicly?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) How do I make an HTTP request in JavaScript?\nb) How do I make an HTTP and HTTPS request in JavaScript?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) How do I really delete my deleted emails?\nb) How can I delete my old emails?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) What is the fastest way to earn money using the Internet?\nb) What is the best way to make money online?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) Is the PS4 or the Xbox One better?\nb) Should I buy the PS4 or Xbox One?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) How many keywords are there in C++ Programming Language in the latest version?\nb) How many keywords are there in C Programming Language in the latest version?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) What is the heat capacity of iron?\nb) What is heat capacity?"}], "ideal": "N"}
{"input": [{"role": "system", "content": "Your task is to classify if the two questions are paraphrases of each other (have the same meaning). You must answer with \"Y\" or \"N\" (without punctuation)."}, {"role": "user", "content": "a) How do I make an HTTP request in TypeScript using Fetch API?\nb) How do I make an HTTPS request in TypeScript using Fetch API?"}], "ideal": "Y"}