Jenseits von grundlegendem Prompting — fortgeschrittene Techniken wie Few-Shot, Chain-of-Thought, strukturierte Ausgaben, System Prompts und weitere — verbessern die Ergebnisse von LLMs erheblich für komplexe Aufgaben. Das Verständnis dafür hilft, das Maximum aus LLMs herauszuholen.
Wichtigste fortgeschrittene Techniken
✓ FEW-SHOT → provide EXAMPLES of input/output in the prompt → the model follows the pattern
(great for specific formats/behaviors); ZERO-SHOT = no examples (just instructions)
✓ CHAIN-OF-THOUGHT (CoT) → ask the model to REASON step by step ('think step by step') →
improves complex reasoning/math (shows its work → more accurate)
✓ STRUCTURED OUTPUT → ask for a specific format (JSON, etc.) → reliable parsing for app
integration (often with schemas/tools)
✓ SYSTEM PROMPTS → set overall behavior/role/rules (the model's persistent instructions)
✓ ROLE/persona → 'You are an expert X' → frames responses
