invert-string eval

[ach-in]

Eval details 📑

Eval name

invert-string eval

Eval description

Test the model's ability to answer basic questions after inverting string word wise twice.

What makes this a useful eval?

Humans find it super easy to follow instructions on inverting strings, and then answer questions, LLMs struggle. Logically, inverting strings twice just results in the original string again. The LLMs find it very difficult to deduce it, and somehow (at least up to GPT-3.5) mix things up.

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 100 high quality examples (it is okay to only contribute 5-10 meaningful examples and have us test them with GPT-4 before adding all 100)

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}.jsonl
• [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
• [ ] (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": "You are a helpful assistant who answers with just one char (capital Y or N)."}, {"role": "user", "content": "Will give a sentence, invert the words one by one (ex. (pens on the table) becomes (snep no eht elbat)). Now repeat the same process again to the sentence thus formed. Then answer if the statement that you get after these opeations is the same as the initial statement. - There are 2 blue pens, 3 red pens. what is the probability to pick red pen at random? -  Only answer with Y or N"}], "ideal": "Y"}
{"input": [{"role": "system", "content": "You are a helpful assistant who answers with just one char (capital Y or N)."}, {"role": "user", "content": "Will give a sentence, invert the words one by one (ex. (pens on the table) becomes (snep no eht elbat)). Now repeat the same process again to the sentence thus formed. Then answer if the statement that you get after these opeations is the same as the initial statement. - I enjoy listening to music. -  Only answer with Y or N"}], "ideal": "Y"}
{"input": [{"role": "system", "content": "You are a helpful assistant who answers with just one char (capital Y or N)."}, {"role": "user", "content": "Will give a sentence, invert the words one by one (ex. (pens on the table) becomes (snep no eht elbat)). Now repeat the same process again to the sentence thus formed. Then answer if the statement that you get after these opeations is the same as the initial statement. - She is a talented artist. -  Only answer with Y or N"}], "ideal": "Y"}
{"input": [{"role": "system", "content": "You are a helpful assistant who answers with just one char (capital Y or N)."}, {"role": "user", "content": "Will give a sentence, invert the words one by one (ex. (pens on the table) becomes (snep no eht elbat)). Now repeat the same process again to the sentence thus formed. Then answer if the statement that you get after these opeations is the same as the initial statement. - We went to the store to buy some groceries. -  Only answer with Y or N"}], "ideal": "Y"}
{"input": [{"role": "system", "content": "You are a helpful assistant who answers with just one char (capital Y or N)."}, {"role": "user", "content": "Will give a sentence, invert the words one by one (ex. (pens on the table) becomes (snep no eht elbat)). Now repeat the same process again to the sentence thus formed. Then answer if the statement that you get after these opeations is the same as the initial statement. - He loves to read books. -  Only answer with Y or N"}], "ideal": "Y"}
{"input": [{"role": "system", "content": "You are a helpful assistant who answers with just one char (capital Y or N)."}, {"role": "user", "content": "Will give a sentence, invert the words one by one (ex. (pens on the table) becomes (snep no eht elbat)). Now repeat the same process again to the sentence thus formed. Then answer if the statement that you get after these opeations is the same as the initial statement. - They are planning a trip to Europe. -  Only answer with Y or N"}], "ideal": "Y"}
{"input": [{"role": "system", "content": "You are a helpful assistant who answers with just one char (capital Y or N)."}, {"role": "user", "content": "Will give a sentence, invert the words one by one (ex. (pens on the table) becomes (snep no eht elbat)). Now repeat the same process again to the sentence thus formed. Then answer if the statement that you get after these opeations is the same as the initial statement. - She has a beautiful singing voice. -  Only answer with Y or N"}], "ideal": "Y"}