[Eval] Add Chinese Homophonic (openai#1169)

# 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 be 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 it 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.**

Also, please note that we're using **Git LFS** for storing the JSON
files, so please make sure that you move the JSON file to Git LFS before
submitting a PR. Details on how to use Git LFS are available
[here](https://git-lfs.com).

## Eval details 📑

### Eval name

Understand Chinese Homophonic 

### Eval description

We have found some popular homophonic sentences on the Internet,
including the Chinese pronunciation of English words and homophones, and
provide several options for the model to determine which option matches
the homophonic sentence the best.

### What makes this a useful eval?

Chinese homophonic puns are a widely popular internet cultural
phenomenon that generates humor by utilizing the homophonic
relationships between Chinese characters. These puns are typically
spread in text form on social media, forums, and messaging applications,
and they are extremely common in China's online culture.

Homophonic puns have a wide range of applications, encompassing ordinary
daily life scenarios as well as hot news events, entertainment gossip,
and political current affairs. These puns frequently appear in internet
memes, jokes, advertising slogans, and short videos, garnering
significant popularity among young people and internet users.

For those unfamiliar with them, homophonic puns may seem like encrypted
text, making it difficult to grasp the true intention behind them.
However, understanding them allows for the establishment of strong
connections between individuals and facilitates smooth communication.

## 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

> 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 commits on 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 acknowledgment

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 the 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 be
granted.

### Submit eval

- [x] I have filled out all required fields of this form
- [x] I have used **Git LFS** for the Eval JSON data
- [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:

<details>
  <summary>View evals in JSON</summary>

  ### Eval
  ```jsonl
{"input": [{"role": "system", "content": "The following are multiple
choice questions (with answers) about Chinese homonym. Answer the
question with english letter \"A\", \"B\" only, without explanation.
Reply with only the option letter."}, {"role": "user", "content":
"一天小鸭对小鸡表白:小鸡，我爱你。小鸡:你duck不必。这句话中的\"duck\"是什么意思？\nA. 鸭子\nB. 大可"}],
"ideal": ["B"]}
{"input": [{"role": "system", "content": "The following are multiple
choice questions (with answers) about Chinese homonym. Answer the
question with english letter \"A\", \"B\" only, without explanation.
Reply with only the option letter."}, {"role": "user", "content":
"丑的人才有对象，美的卖空调。这句话中的\"美的\"是什么意思？\nA. 漂亮的\nB. 空调公司"}], "ideal": ["B"]}
{"input": [{"role": "system", "content": "The following are multiple
choice questions (with answers) about Chinese homonym. Answer the
question with english letter \"A\", \"B\" only, without explanation.
Reply with only the option letter."}, {"role": "user", "content":
"我是一只小绵羊，我今天剪毛了，我失绵了。这句话中的\"失绵\"表达意思？\nA. 失眠\nB. 没有了羊毛"}], "ideal":
["A"]}
{"input": [{"role": "system", "content": "The following are multiple
choice questions (with answers) about Chinese homonym. Answer the
question with english letter \"A\", \"B\" only, without explanation.
Reply with only the option letter."}, {"role": "user", "content":
"以后我的吉祥物决定就是你了，螃蟹！——因为，你有钱（钳）。这句话中的\"钳\"是什么意思？\nA. 有钱\nB. 螃蟹的钳子"}],
"ideal": ["A"]}
{"input": [{"role": "system", "content": "The following are multiple
choice questions (with answers) about Chinese homonym. Answer the
question with english letter \"A\", \"B\" only, without explanation.
Reply with only the option letter."}, {"role": "user", "content":
"女孩对爸爸说\"爸比，我们去哪啊\"爸爸没听见，妈妈笑了一下，女孩对妈妈说\"妈比，你笑什么\"妈妈打了她一巴掌。妈妈为什么打她？\nA.
她提出了不合理的要求\nB. 她骂人了"}], "ideal": ["B"]}
{"input": [{"role": "system", "content": "The following are multiple
choice questions (with answers) about Chinese homonym. Answer the
question with english letter \"A\", \"B\" only, without explanation.
Reply with only the option letter."}, {"role": "user", "content":
"天气这么热，我们总会熟的。这句话中的\"熟的\"是什么意思？\nA. 热熟了\nB. 熟悉了"}], "ideal": ["B"]}
{"input": [{"role": "system", "content": "The following are multiple
choice questions (with answers) about Chinese homonym. Answer the
question with english letter \"A\", \"B\" only, without explanation.
Reply with only the option letter."}, {"role": "user", "content":
"我好像胖了，没事我陪你减肥，我们戒荤叭。这句话中的\"戒荤\"是什么意思？\nA. 吃素食\nB. 结婚"}], "ideal":
["B"]}
  ```
</details>

---------

Co-authored-by: oscar <oscar@hellotalk.com>

evals/registry/evals/chinese_homophonic.yaml

@@ -0,0 +1,9 @@
+chinese-homo:
+  id: chinese-homophonic.dev.v0
+  description: Example eval that checks sampled text matches the expected output.
+  disclaimer: This is an example disclaimer.
+  metrics: [accuracy]
+chinese-homophonic.dev.v0:
+  class: evals.elsuite.basic.match:Match
+  args:
+    samples_jsonl: chinese_homophonic/chinese_homophonic.jsonl