cot-prompting-wei-neurips-2022

Summary

Chain-of-Thought prompting, the technique of asking a model to show its step-by-step reasoning before giving a final answer, was originated by a team at Google Brain and formally presented at NeurIPS in 2022. This matters because it anchors the method to a specific, verifiable publication, so any downstream reasoning that depends on it can be traced back to a known source and date.