|
|
# Evaluate Plato's Dialogue
|
|
|
|
|
|
import { Tabs, Tab } from 'nextra/components'
|
|
|
|
|
|
## Background
|
|
|
The following prompt tests an LLM's ability to perform evaluation on the outputs of two different models as if it was a teacher.
|
|
|
|
|
|
First, two models (e.g., ChatGPT & GPT-4) are prompted to using the following prompt:
|
|
|
|
|
|
```
|
|
|
Plato’s Gorgias is a critique of rhetoric and sophistic oratory, where he makes the point that not only is it not a proper form of art, but the use of rhetoric and oratory can often be harmful and malicious. Can you write a dialogue by Plato where instead he criticizes the use of autoregressive language models?
|
|
|
```
|
|
|
|
|
|
Then, those outputs are evaluated using the evaluation prompt below.
|
|
|
|
|
|
## Prompt
|
|
|
```
|
|
|
Can you compare the two outputs below as if you were a teacher?
|
|
|
|
|
|
Output from ChatGPT: {output 1}
|
|
|
|
|
|
Output from GPT-4: {output 2}
|
|
|
```
|
|
|
|
|
|
## Code / API
|
|
|
|
|
|
<Tabs items={['GPT-4 (OpenAI)', 'Mixtral MoE 8x7B Instruct (Fireworks)']}>
|
|
|
<Tab>
|
|
|
|
|
|
```python
|
|
|
from openai import OpenAI
|
|
|
client = OpenAI()
|
|
|
|
|
|
response = client.chat.completions.create(
|
|
|
model="gpt-4",
|
|
|
messages=[
|
|
|
{
|
|
|
"role": "user",
|
|
|
"content": "Can you compare the two outputs below as if you were a teacher?\n\nOutput from ChatGPT:\n{output 1}\n\nOutput from GPT-4:\n{output 2}"
|
|
|
}
|
|
|
],
|
|
|
temperature=1,
|
|
|
max_tokens=1500,
|
|
|
top_p=1,
|
|
|
frequency_penalty=0,
|
|
|
presence_penalty=0
|
|
|
)
|
|
|
```
|
|
|
</Tab>
|
|
|
|
|
|
<Tab>
|
|
|
```python
|
|
|
import fireworks.client
|
|
|
fireworks.client.api_key = "<FIREWORKS_API_KEY>"
|
|
|
completion = fireworks.client.ChatCompletion.create(
|
|
|
model="accounts/fireworks/models/mixtral-8x7b-instruct",
|
|
|
messages=[
|
|
|
{
|
|
|
"role": "user",
|
|
|
"content": "Can you compare the two outputs below as if you were a teacher?\n\nOutput from ChatGPT:\n{output 1}\n\nOutput from GPT-4:\n{output 2}",
|
|
|
}
|
|
|
],
|
|
|
stop=["<|im_start|>","<|im_end|>","<|endoftext|>"],
|
|
|
stream=True,
|
|
|
n=1,
|
|
|
top_p=1,
|
|
|
top_k=40,
|
|
|
presence_penalty=0,
|
|
|
frequency_penalty=0,
|
|
|
prompt_truncate_len=1024,
|
|
|
context_length_exceeded_behavior="truncate",
|
|
|
temperature=0.9,
|
|
|
max_tokens=4000
|
|
|
)
|
|
|
```
|
|
|
</Tab>
|
|
|
|
|
|
|
|
|
</Tabs>
|
|
|
|
|
|
## Reference
|
|
|
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://arxiv.org/abs/2303.12712) (13 April 2023) |