How Few Shot Demonstrations Affect

Design prompt-based LLM safety defenses using optimal few-shot strategies. Applies the finding that few-shot demonstrations enhance Role-Oriented Prompts (RoP) but degrade Task-Oriented Prompts (ToP). Use when: 'harden my system prompt against jailbreaks', 'add few-shot safety examples', 'design a defense prompt', 'improve LLM safety alignment', 'protect my chatbot from prompt injection', 'write a safe system prompt with examples'.

ndpvt-web Updated 14 repo stars

File contents

ndpvt-web/arxiv-claude-skills commit 2ff90084af

Frequently asked questions

npx get-skill add ndpvt-web/how-few-shot-demonstrations-affect