Saat Anda memberi tahu model untuk menjelaskan penalarannya, model akan merespons dengan langkah-langkah yang digunakan untuk memecahkan masalah. Melalui proses ini terkadang dapat meningkatkan akurasi dan nuansa, terutama untuk kueri yang sulit.
Langkah-langkah penalaran disertakan sebagai bagian dari respons. Untuk menguraikan langkah-langkah penalaran dari jawaban yang Anda cari, Anda dapat menentukan format output menggunakan XML atau pemisah lainnya.
Contoh
Misalnya, Anda menulis blog memasak dan ingin model tersebut memberi tahu Anda bagaimana pembaca dapat menafsirkan berbagai bagian blog. Jika Anda tidak menginstruksikan model untuk menjelaskan alasannya, respons dari model mungkin tidak berguna seperti yang Anda inginkan:
| Tidak ada alasan |
|---|
What is the most likely interpretation of this sentence?
The sentence: "The chef seasoned the chicken and put it in the oven because it looked pale."
The chef seasoned the chicken and put it in the oven because it lacked color and needed cooking.
|
Meskipun Anda telah mempelajari cara model memprediksi pembaca mungkin menafsirkan kalimat, sebaiknya Anda memahami lebih lanjut prediksi spesifik yang dibuat model untuk menghasilkan respons. Seperti yang ditunjukkan dalam contoh berikut, kualitas respons juga dapat ditingkatkan:
| Menjelaskan alasan |
|---|
What is the most likely interpretation of this sentence? Explain your reasoning
The sentence: "The chef seasoned the chicken and put it in the oven because it looked pale."
Interpreting "The chef seasoned the chicken and put it in the oven because it looked pale."
The most likely interpretation is that the chef seasoned the chicken to add flavor and color, then put it in the oven to cook it.
Here's the reasoning:
- Seasoning is typically used to enhance the flavor of food. Chefs often use spices, herbs, and other ingredients to make their dishes more appealing.
- "Pale" suggests the chicken lacked visual appeal before being seasoned. This could imply it was unseasoned or simply lacking color from spices.
- Putting the chicken in the oven is a common cooking method. The sentence implies the chef's intention is to cook the chicken, not just season it.
Therefore, the chef's actions are likely aimed at both improving the taste and appearance of the chicken through seasoning and then cooking it in the oven.
|
Teknik lain yang dapat Anda gunakan untuk meningkatkan respons model adalah dengan menginstruksikan model untuk berpikir langkah demi langkah dan menjelaskan penalarannya. Hal ini mengharuskan model untuk membagi input menjadi beberapa langkah dan memberikan alasan yang digunakan untuk memecahkan masalah:
| Berpikir langkah demi langkah |
|---|
What is the most likely interpretation of this sentence? Think step by step and print out
the thinking process.
Please output in JSON format with final answer in 'answer', and thinking steps in 'think' fields.
The sentence: "The chef seasoned the chicken and put it in the oven because it looked pale."
{
"answer": "The chef seasoned the chicken to enhance its flavor and put it in the oven to cook it because it appeared to be undercooked.",
"think": [
{
"step": 1,
"thought": "The chef seasoned the chicken. This suggests that the chef is preparing the chicken for cooking."
},
{
"step": 2,
"thought": "The chef put the chicken in the oven. This indicates that the chef is cooking the chicken."
},
{
"step": 3,
"thought": "The sentence states that the chicken looked pale. Pale chicken is often undercooked."
},
{
"step": 4,
"thought": "Combining these observations, it is most likely that the chef seasoned the chicken to enhance its flavor and put it in the oven to cook it because it appeared to be undercooked."
}
]
}
|
Dengan meminta model untuk mencetak proses pemikirannya, model akan menghasilkan respons yang lebih menyeluruh dan Anda akan mempelajari lebih lanjut cara model menghasilkan respons tersebut.
Langkah selanjutnya
- Jelajahi contoh perintah lainnya di Galeri perintah.