Update ape.en.mdx
The Automatic Prompt Engineer paper claims that this prompt elicits better results: "Let’s work this out **in** a step by step **way** to be sure we have the right answer." But the prompt in the ape.en.mdx file misquotes the prompt: "Let’s work this out **it** a step by step to be sure we have the right answer."pull/109/head
parent
263c57ab2f
commit
c0ace7c241
|
@ -14,7 +14,7 @@ The first step involves a large language model (as an inference model) that is g
|
||||||
|
|
||||||
APE discovers a better zero-shot CoT prompt than the human engineered "Let's think step by step" prompt ([Kojima et al., 2022](https://arxiv.org/abs/2205.11916)).
|
APE discovers a better zero-shot CoT prompt than the human engineered "Let's think step by step" prompt ([Kojima et al., 2022](https://arxiv.org/abs/2205.11916)).
|
||||||
|
|
||||||
The prompt "Let's work this out it a step by step to be sure we have the right answer." elicits chain-of-though reasoning and improves performance on the MultiArith and GSM8K benchmarks:
|
The prompt "Let’s work this out in a step by step way to be sure we have the right answer." elicits chain-of-though reasoning and improves performance on the MultiArith and GSM8K benchmarks:
|
||||||
|
|
||||||
<Screenshot src={APECOT} alt="APECOT" />
|
<Screenshot src={APECOT} alt="APECOT" />
|
||||||
Image Source: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)
|
Image Source: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)
|
||||||
|
|
Loading…
Reference in New Issue