From e37798a50c00d89242d744d9c83fba09b98e2e15 Mon Sep 17 00:00:00 2001 From: Jeremy Zucker Date: Sun, 9 Apr 2023 13:54:50 -0400 Subject: [PATCH] Update ape.en.mdx The single-quote was in unicode, so I changed it to ascii for greater compatibility across browsers. --- pages/techniques/ape.en.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/techniques/ape.en.mdx b/pages/techniques/ape.en.mdx index b6086b6..e613e66 100644 --- a/pages/techniques/ape.en.mdx +++ b/pages/techniques/ape.en.mdx @@ -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 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: +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: Image Source: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)