Prompt EngineeringMichihiro Yasunaga et al. (Google DeepMind, Stanford)Google DeepMindStanford University
Analogical Prompting published
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Analogical Prompting published — the model generates relevant examples itself, then solves the problem
Why it matters
A branch that gets the few-shot effect without labeling examples
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2310.01714Added in Week 35, 2026 · See that week
On the map — ① Prompt Engineering line
- Previous stopChain-of-Verification
- This recordAnalogical Prompting
- Next stopGPT-4.1