Nhắc tự thống nhất

Có lẽ một trong những kỹ thuật tiên tiến hơn dành cho kỹ thuật nhắc đó là tính tự nhất quán. Đề xuất bởi Wang et al. (2022), tính tự nhất quán nhằm “thay thế cách giải mã tham lam đơn giản được sử dụng trong phương pháp gợi ý suy luận từng bước CoT”. Ý tưởng là lấy mẫu nhiều lối suy luận few-shot thông qua CoT vài lần và sử dụng các kết quả để chọn ra câu trả lời nhất quán nhất. Điều này giúp nâng cao hiệu suất của nhắc CoT đối với các nhiệm vụ liên quan đến lý luận số học và thông thường.

Hãy thử ví dụ sau để suy luận số học:

Lời nhắc:

When I was 6 my sister was half my age. NowI’m 70 how old is my sister?

Đầu ra:

35

Đầu ra sai! Làm thế nào chúng ta có thể cải thiện điều này với sự tự nhất quán? Hãy thử nó. Chúng tôi sẽ sử dụng các ví dụ về few-shot từ Wang và cộng sự đã thực hiện:

Lời nhắc:

Q: There are 15 trees in the grove. Grove workers will plant trees in the grove today. After they are done,
there will be 21 trees. How many trees did the grove workers plant today?
A: We start with 15 trees. Later we have 21 trees. The difference must be the number of trees they planted.
So, they must have planted 21 - 15 = 6 trees. The answer is 6.
Q: If there are 3 cars in the parking lot and 2 more cars arrive, how many cars are in the parking lot?
A: There are 3 cars in the parking lot already. 2 more arrive. Now there are 3 + 2 = 5 cars. The answer is 5.
Q: Leah had 32 chocolates and her sister had 42. If they ate 35, how many pieces do they have left in total?
A: Leah had 32 chocolates and Leah’s sister had 42. That means there were originally 32 + 42 = 74
chocolates. 35 have been eaten. So in total they still have 74 - 35 = 39 chocolates. The answer is 39.
Q: Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12 lollipops. How many lollipops
did Jason give to Denny?
A: Jason had 20 lollipops. Since he only has 12 now, he must have given the rest to Denny. The number of
lollipops he has given to Denny must have been 20 - 12 = 8 lollipops. The answer is 8.
Q: Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does
he have now?
A: He has 5 toys. He got 2 from mom, so after that he has 5 + 2 = 7 toys. Then he got 2 more from dad, so
in total he has 7 + 2 = 9 toys. The answer is 9.
Q: There were nine computers in the server room. Five more computers were installed each day, from
monday to thursday. How many computers are now in the server room?
A: There are 4 days from monday to thursday. 5 computers were added each day. That means in total 4 * 5 =
20 computers were added. There were 9 computers in the beginning, so now there are 9 + 20 = 29 computers.
The answer is 29.
Q: Michael had 58 golf balls. On tuesday, he lost 23 golf balls. On wednesday, he lost 2 more. How many
golf balls did he have at the end of wednesday?
A: Michael initially had 58 balls. He lost 23 on Tuesday, so after that he has 58 - 23 = 35 balls. On
Wednesday he lost 2 more so now he has 35 - 2 = 33 balls. The answer is 33.
Q: Olivia has $23. She bought five bagels for $3 each. How much money does she have left?
A: She bought 5 bagels for $3 each. This means she spent $15. She has $8 left.
Q: When I was 6 my sister was half my age. Now I’m 70 how old is my sister?
A:

Đầu ra 1:

When I was 6 my sister was half my age, so she was 3. Now I am 70, so she is 70 - 3 = 67. The answer is 67.

Đầu ra 2:

When the narrator was 6, his sister was half his age, which is 3. Now that the narrator is 70, his sister would be 70 - 3 = 67 years old. The answer is 67.

Đầu ra 3:

When I was 6 my sister was half my age, so she was 3. Now I am 70, so she is 70/2 = 35. The answer is 35.

Việc tính toán để tìm ra câu trả lời cuối cùng bao gồm một số bước (xem bài báo để biết chi tiết) nhưng để đơn giản, chúng ta có thể thấy rằng đã có đa số câu trả lời xuất hiện nên về cơ bản nó sẽ trở thành câu trả lời cuối cùng.