IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies
IHDec (Instruction Hierarchy-steered Decoding) leverages JSD to automatically detect token-level hierarchy violations and dynamically executes contrastive decoding to suppress misaligned subordinate roles, and outperforms training-based baselines in multi-turn conflicts while fully preserving general response quality.