Instruction Hierarchy
The instruction hierarchy is a training approach that teaches a model to prioritize instructions by source, typically system over user over tool output, and to ignore lower-priority instructions that conflict with higher-priority ones.
Description
Wallace et al. trained models on synthetic conflicts and found large gains in robustness to prompt injection and system-prompt extraction with limited loss in helpfulness.
Sources
- Wallace et al. (2024). The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.
Cite this entry
Protologue. (2026). Instruction Hierarchy. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0093). https://protologue.com/t/instruction-hierarchy/
BibTeX
@misc{protologue_instruction_hierarchy,
title = {Instruction Hierarchy},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0093},
url = {https://protologue.com/t/instruction-hierarchy/}
}