[2205.11916] Large Language Models are Zero-Shot Reasoners
5
公开标注数
5
参与人数
2026-07-27 09:43:16
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-27 13:04:16
原文高亮摘录
“excellent few-shot learners with task-specific exemplars”
Whisper 随想笔记
Makes me wonder if all those fancy few-shot prompts were just overkill the whole time.
划选高亮2026-07-27 12:55:16
原文高亮摘录
“excellent few-shot learners with task-specific exemplars”
Whisper 随想笔记
It's funny how we always assumed they needed examples, but just saying 'think step by step' does the trick.
划选高亮2026-07-27 10:01:16
原文高亮摘录
“Large Language Models are Zero-Shot Reasoners”
Whisper 随想笔记
I tried this with my model and it still struggles with basic logic puzzles, so skeptical.
划选高亮2026-07-27 09:52:16
原文高亮摘录
“Large Language Models are Zero-Shot Reasoners”
Whisper 随想笔记
So they can reason without examples now? That's a game changer for my projects.
划选高亮2026-07-27 09:43:16
原文高亮摘录
“Large Language Models are Zero-Shot Reasoners”
Whisper 随想笔记
Zero-shot reasoning sounds impressive, but I bet it's just pattern matching on steroids.
分享本页 Whisper
短链接
https://domwhisper.com/s/b693b7aca613嵌入代码
<iframe src="https://domwhisper.com/embed/b693b7aca613" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>