From c369cb4ae17a65c3e4cceb49af3d92c25d4d2649 Mon Sep 17 00:00:00 2001 From: RainBus Date: Sun, 29 Sep 2024 16:06:10 +0800 Subject: [PATCH] vault backup: 2024-09-29 16:06:10 --- Record/DL/CoT Prompt.md | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/Record/DL/CoT Prompt.md b/Record/DL/CoT Prompt.md index 2834df3..6ac9bef 100644 --- a/Record/DL/CoT Prompt.md +++ b/Record/DL/CoT Prompt.md @@ -1,12 +1,13 @@ -## Standard Prompt - +## Standard Few-shot Prompt +Prompt: `Q(question) + A(answer)` > **Model Input:** Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now? > A: The answer is 11. > Q: The cafeteria had 23 apples. If they used 20 to make lunch and bought 6 more, how many apples do they have? > **Model Output:** A: The answer is 27.（x） -## Few-shot-CoT -Prompt: `rationale(r) + answer(a)` +## Few-shot CoT +思维链提示，就是把一个多步骤推理问题，分解成很多个中间步骤，分配给更多的计算量，生成更多的 token，再把这些答案拼接在一起进行求解。 +Prompt: Q + A(r(rationale) + a(answer)) Answer: LLM同样会给出理由和答案。 > **Model Input:** Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now? @@ -14,4 +15,6 @@ Answer: LLM同样会给出理由和答案。 > Q: The cafeteria had 23 apples. If they used 20 to make lunch and bought 6 more, how many apples do they have? > **Model Output:** A: The cafeteria had 23 apples originally. They used 20 to make lunch. So they had 23 - 20 = 3. They bought 6 more apples, so they have 3 + 6 = 9. The answer is 9. -思维链提示，就是把一个多步骤推理问题，分解成很多个中间步骤，分配给更多的计算量，生成更多的 token，再把这些答案拼接在一起进行求解。 \ No newline at end of file +## Zero-shot CoT +通过 `Let's think step by step` 可以让 LLM 生成回答问题的思维链。我们可以将 Zero-shot CoT 看作一个 pipeline，我们先使用 `Let's think step by step` 让 LLM 尽可能生成一些思考过程，然后将生成的 rationale 和 question 拼接起来，重新配合一个指向 answer 的 Prompt 来激励模型生成答案。 +Prompt: Q + Let's think step by step ｜ LLM | Q + (上一步的输出) + The answer is | LLM ｜ Output \ No newline at end of file