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)).
|
||||
|
||||
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" />
|
||||
Image Source: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)
|
||||
|
@ -23,4 +23,4 @@ This paper touches on an important topic related to prompt engineering which is
|
|||
|
||||
- [AutoPrompt](https://arxiv.org/abs/2010.15980) - proposes an approach to automatically create prompts for a diverse set of tasks based on gradient-guided search.
|
||||
- [Prefix Tuning](https://arxiv.org/abs/2101.00190) - a lightweight alternative to fine-tuning that prepends a trainable continuous prefix for NLG tasks.
|
||||
- [Prompt Tuning](https://arxiv.org/abs/2104.08691) - proposes a mechanism for learning soft prompts through backpropagation.
|
||||
- [Prompt Tuning](https://arxiv.org/abs/2104.08691) - proposes a mechanism for learning soft prompts through backpropagation.
|
||||
|
|
Loading…
Reference in New Issue