“But in fact just prompting a model like GPT-3 or Gopher with "let's think step by step" and letting it process in context is already significantly improving performance on wide variety of reasoning tasks [0].”
Large Language Models are Zero-Shot Reasoners
只加一句“让我们一步步思考”,LLM 的零样本推理大幅提升
论文表明,只要在每个回答前加上“Let's think step by step”,LLM 就是不错的零样本推理者。这个称为 Zero-shot-CoT 的单一提示模板,无需手写少样本示例,就在算术、符号推理和其他逻辑推理基准上显著超过普通零样本表现,例如用 text-davinci-002 把 MultiArith 的准确率从 17.7% 提到 78.7%,GSM8K 从 10.4% 提到 40.7%,540B 的 PaLM 上也有类似幅度的提升。作者希望它成为这些推理基准上最简单而强的零样本基线。
评论者把它当作“Let's think step by step”提示技巧和零样本思维链的出处,用来说明 LLM 的推理表现不是单靠记忆或模式匹配。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“Even the classic "let's think about this step by step" paper came out less than a year ago: Large Language Models are Zero-Shot Reasoners - May 2022.”
“difficult system-2 tasks that do not follow the standard scaling laws for LLMs Large Language Models are Zero-Shot Reasoners”
“[1] Large Language Models are Zero-Shot Reasoners - Large Language Models are Zero-Shot Reasoners”
“"Let's think step by step:" at the end of your prompt is probably the best-known one: Large Language Models are Zero-Shot Reasoners”
“the title of which is, I believe, the source of the”
看全部 13 条 →
“1: Large Language Models are Zero-Shot Reasoners”
“even something as simple as a zero shot prompt followed by "let's think step by step" has significant improvement: Large Language Models are Zero-Shot Reasoners”
“their performance at zero-shot problems is simply impossible through pure memorisation or pattern-matching”
“to elicit a chain-of-thought response. See: Large Language Models are Zero-Shot Reasoners”
“[2] - Large Language Models are Zero-Shot Reasoners”
“This technique and name stem from the early observation that LLMs do better when explicitly told to”
“Since roughly 2022, they understand that they are working with systems capable of reasoning: Large Language Models are Zero-Shot Reasoners”
- Large Language Models are Zero-Shot Reasoners: Let's think step by step ↗HammadB · 2022-05-25 · 4 分
- Large Language Models Are Zero-Shot Reasoners ↗archon1410 · 2022-05-28 · 1 分