Prompting and context design · MLD-0565
Instruction hierarchy
A prioritization scheme for resolving conflicts among instruction sources.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Distinguish application policy from quoted document instructions.
Original caveat
The hierarchy must be supported by training and system controls.
Context and aliases
Level: Intermediate. Stages: Inference · Evaluation.
Tags: SLM · LLM · NLP.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Anthropic: Building effective agents ↗ · Reference link
- Hugging Face: chat templates ↗ · Reference link
- Anthropic: Effective context engineering for AI agents ↗ · Reference link
- Transformers glossary ↗ · Consulted
- Original reference URL ↗