Usage Recommendation for DeepSeek-R1
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
Key pointsThis work provides a set of recommendations for how to prompt the DeepSeek-R1 model. Below are the key guidelines: 1. Prompt Engineering:
01
Use clear, structured prompts with explicit instructions
02
Avoid few-shot prompting; use zero-shot instead 1. Output Formatting:
03
Specify the desired format (JSON, tables, markdown)
04
Request step-by-step explanations for reasoning tasks 1. Language:
05
Explicitly specify input/output language to prevent mixing The paper also summarizes when to use the different model variants, when to fine-tune, and other safety considerations.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack