precondition-callout-Accuracy1.0

[Masayoshi555]

Eval details 📑

#Eval name preconditions-callout

#Eval description This eval tests ChatGPT's ability to understand and provide information from a hierarchically structured data set. The data set contains directory names, and users will request information from specific directories. The code for this feature has been tested and achieved 100% accuracy.

#What makes this a useful eval? This eval is useful because it tests the model's ability to interpret and provide information based on hierarchical structures, which is a common way data is organized in real-world applications. It demonstrates the model's capability to understand context and navigate complex data structures to deliver accurate responses.

Criteria for a good eval ✅

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 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 This eval specifically targets the model's ability to understand hierarchical data structures, which is a valuable skill for AI systems in practical applications.

Eval structure 🏗️

Your eval should

• [✅]Check that your data is in evals/registry/data/{name}
• [✅]Check that your yaml is registered at evals/registry/evals/{name}.yaml
• [✅]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).

• [✅]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.

• [✅]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
• [✅]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 jsonl Copy code { "input": "What information is stored in the 'projects' directory?", "target": "The 'projects' directory contains information about various ongoing projects, such as their status, team members, and progress." }, { "input": "What value is directory1?", "target": "finances" }, { "input": "Where is human_resource directory?", "target": "directory2-2" }, { "input": "Please enumerate the value of directories under directory3", "target": "Research, Development" }

[Masayoshi555]

@SierotkaM
Thank you for reviewing 😄

I don't know your language. But Google translate answered that your language is Polish. And, you pointed out that this model is fragile.

Can you tell us a definition of vulnerability in eval? In other words, how can we say it is stable?

In this case, you have shown that you can reliably call out preconditions by adhering to the rules of input, but do you want to be able to call them out without adhering to the rules of input? Do you want to be able to pull it out even if you don't have to follow the input rules?

And, must I modify model? Can you merge as it is?

[usama-openai]

Closing the PR due to inactivity; please feel free to reopen if you get a chance to address the comments.