LLM มีความสามารถที่แข็งแกร่งในการสร้างข้อความที่สอดคล้องกัน การใช้กลยุทธ์พร้อมท์ที่มีประสิทธิภาพสามารถกำหนดทิศทางแบบจำลองเพื่อสร้างการตอบสนองที่ดีขึ้น สม่ำเสมอ และเป็นข้อเท็จจริงมากขึ้น LLM ยังมีประโยชน์อย่างยิ่งสำหรับการสร้างข้อมูลซึ่งมีประโยชน์มากในการทำการทดลองและการประเมินผลทุกประเภท ตัวอย่างเช่น เราสามารถใช้มันเพื่อสร้างตัวอย่างด่วนสำหรับตัวแยกประเภทความรู้สึก เช่น:
Prompt:
Produce 10 exemplars for sentiment analysis. Examples are categorized as either positive or negative. Produce 2 negative examples and 8 positive examples. Use this format for the examples:
Q: <sentence>
A: <sentiment>
Output:
Q: I just got the best news ever!
A: Positive
Q: We just got a raise at work!
A: Positive
Q: I'm so proud of what I accomplished today.
A: Positive
Q: I'm having the best day ever!
A: Positive
Q: I'm really looking forward to the weekend.
A: Positive
Q: I just got the best present ever!
A: Positive
Q: I'm so happy right now.
A: Positive
Q: I'm so blessed to have such an amazing family.
A: Positive
Q: The weather outside is so gloomy.
A: Negative
Q: I just got some terrible news.
A: Negative
สิ่งนี้มีประโยชน์มาก จริงๆ แล้ว เราใช้ตัวอย่างนี้สำหรับการทดสอบอื่นในส่วนอื่นของคำแนะนำ