Self-Instruct构造Prompt的例子

1. 人工构造一批Prompt做种子。（Starting with a small seed set of human-written tasks）
2. 每次把一些种子+后来生成的Prompt，放到Input里做few-shot examples，用LLM生成更多的Prompt；（Using the LLM to generate new instructions based on the seed tasks）
3. 过滤掉质量太差的，修正能要的；（Filtering and refining the generated instructions）
4. 把生成的所有Prompt，输入LLM得到输出结果；（Creating input-output instances for the new instructions）
5. Input+Output，做LLM的训练样本（Using the generated dataset to fine-tune the LLM）

第2步，LLM生成：

import random
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load a pre-trained language model
model_name = "bigcode/starcoderbase-1b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Seed tasks (simplified for demonstration)
seed_tasks = [
    "Write a function to calculate the factorial of a number.",
    "Create a class to represent a bank account.",
    "Implement a binary search algorithm."
]

def generate_instruction(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=50)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

def self_instruct(num_iterations):
    generated_tasks = []
    
    for _ in range(num_iterations):
        # Sample existing tasks
        sampled_tasks = random.sample(seed_tasks + generated_tasks, min(3, len(seed_tasks) + len(generated_tasks)))
        
        # Create a prompt for generating new instructions
        prompt = "Generate a new programming task based on these examples:\n\n"
        prompt += "\n".join(sampled_tasks)
        prompt += "\n\nNew task:"
        
        # Generate a new instruction
        new_task = generate_instruction(prompt)
        
        # In practice, you would filter and refine the generated task here
        
        generated_tasks.append(new_task)
    
    return generated_tasks

# Run Self-Instruct
new_tasks = self_instruct(5)
for i, task in enumerate(new_tasks, 1):
    print(f"Task {i}: {task}")

第3步过滤：

人工定义一些规则，过滤掉太差的；（也可以用LLM来做裁判）

目的：确保质量和多样性；

• Filter out instructions that are too short or too long
• Filter out instructions containing keywords unsuitable for language models (e.g. "image", "graph", "file", "plot")
• Filter out instructions starting with punctuation
• Filter out instructions starting with non-English characters
• Filter out instructions that have high ROUGE-L similarity (above 0.7) with any existing instruction in the task pool